Blog
- Subset Collections:
- Lab Seminars
- [Choe]-tagged
Subscribe: Facebook group.
This is mostly a collection of articles I found to be interesting. The ones marked “[Choe]” are original articles or those that include my commentary.
- [New] 2/26/2022: You can now press the [ j ] and [ k ] key inside the article to go back and forth between the articles, and [ l ] key to come back to the listing.
- Copying over articles from my private Facebook group is now complete (2020 to present).
- Old articles from my private collection are now also available (2013 to 2017, and 2017 to 2019).
- Lab seminar materials have been added. See /seminar/ for a separate collection of only these entries.
Enjoy!
- 2024
- Justin Wood: Radical Empiricism: The origins of knowledge as a mini-evolution
- [Lab Seminar] Fall 2024 Archive
- [Choe] Braitenberg vehicle simulator using ChatGPT+Claude
- [Prediction][Autism] Your brain is ahead, predicting the world, and implcations on autism
- [LLM][Hinton] Will digital intelligence replace biological intelligence : Geoff Hinton
- [LLM][Hinton] Will digital intelligence replace biological intelligence : Geoff Hinton
- [Philisophy] Can computers think? No. They cant actually do anything. Alva Noe
- [Connectome][Fly] Entire fly brain mapped: Sebastian Seung and Colleagues at Princeton
- [World Model] World Labs by Feifei Li
- [Neuroscience][Deep Learning] Andrew Saxe : What does deep learning imply about cognition
- [Philosophy][LLM] Chatbot Epistemology - Susan Schneider
- [Consciousness][Sensorimotor][Penrose][Choe] Consciousness and microtubules
- [Consciousness][Prediction] Study reveals how an anesthesia drug incudes unconsciousness
- [Neuroscience] The neuron as a direct data-driven controller PNAS
- [Choe][Lab][Consciousness][Meaning] My talk at the NORDTEK conference
- [Career] Good career advice by founder of 3Blue1Brown
- [Dennett][Philosophy][Consciousness] Obituary of Daniel Dennet by John Horgan
- [Lab Seminar] Spring 2024 Archive
- [OpenAI][GPT] ChatGPT's ancestor GPT-2 jammed into 1.25GB Excel sheet - LLM runs inside a spreadsheet that you can download from GitHub
- [Clark][Consciousness][Prediction] How the brain shapes reality - with Andy Clark
- [Penrose][Time][Consciousness] Testing A Time-Jumping, Multiverse-Killing, Consciousness-Spawning Theory Of Reality
- [Google][DeepMind] Genie: Generative interactive environments
- [Miikkulainen][GenAI] Generative AI: an AI paradigm shift in the making?
- [OpenAI][Sora] Sora: Creating video from text
- [LeCun][AGI] Meta AI Chief Yann LeCun on AGI, Open-Source, and AI Risk
- [Meta][AGI][Zuckerberg] Zuckerberg now wants to focus on AGI
- 2023
- [Lab Seminar] 2023 Fall Archive
- The computational theory of mind
- [LLM] Using AI to decode animal communication with Aza Raskin
- [LLM] A test of artificial intelligence
- [Humphrey][Consciousness] How did consciousness evolve, by Nicholas Humphrey
- [LLM][Embodied] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
- [Consciousness][Bengio][ASSC] Yoshua Bengio: Sources of richness and ineffability for phenomenal conscious states
- [LLM][NPC][Game][Agent] Generative Agents: Interactive Simulacra of Human Behavior
- [Time][Memory][Life] Time is fundamental to the emergence of life
- [Lab Seminar] 2023 Spring Archive
- [Prediction] Emergence of a predictive model in the hippocampus
- [DL][Book] New deep learning book by Simon Prince
- [LLM][Multimodal] PaLM-E: An Embodied Multimodal Language Model
- [LLM][Meaning][NLP] Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
- [Consciousness][Damasio] Feelings are the source of consciousness
- [Consciousness] Artificial Conciousness is Impossible, by David Hsing
- [LLM] The end of programming
- [GAN][DALL-E] Modern Generative AI: An Overview, by Sergey Nikolenko
- 2022
- [Lab Seminar] 2022 Archive
- [NeurIPS][LLM][RL][Consciousness] NeurIPS 2022
- [Vision][Consciousness][ORegan][Choe] Recent Trends in Visual Cognition Workshop
- [ChatGPT][LLM][Choe] More fun with ChatGPT
- [OpenAI][GPT][Choe] OpenAI: ChatGPT - quite good
- [Neuroevolution][Evolution] Prof. Risto Miikkulainen's tutorial on neuroevolution (GECCO 2022)
- [Olfaction][Hippocampus][Choe] An intrinsic association between olfactory identification and spatial memory in humans
- [Open-ended][Minecraft] Building open-ended embodied agents with internet-scale knowledge
- [Autonomous Driving][Kwon] Have we been thinking about autonomous driving all wrong?
- [BeyondDL][Molnar][Choe] Beyond Benchmark Islands
- [DeepMind][AGI] DeepMind researcher claims new AI could lead to AGI
- [NeurIPS][Workshop] I cannot believe it's not better
- [Neuroscience][Transformer] How AI Transformers Mimic Parts of the Brain
- [OpenAI][Stanley][Evolution][LM] Intelligent Mutations in Genetic Programming: OpenAI Proposes Evolution Through Large Models
- [LeCun] A path towards autonomous machine intelligence
- [DataPruning][Meta] Meta develops dateset pruning technique for scaling AI learning
- [Spider][Dream][Consciousness] Rapid-Eye-Movement sleep-like behavior in jumping spiders
- [NLP][LM] Inside a Radical New Project to Democratize AI
- [DeepMind][Hassabis][LexFridman] Lex Fridman interviews Demis Hassabis
- [Tool] A framework for tool cognition in robots without prior tool learning or observation
- [LeCun][Symbolic] What AI Can Tell Us About Intelligence
- [OpenAI][RL] Learning to play Minecraft with Video PreTraining (VPT)
- [Consciousness][Choe] The mind is more than a machine
- [LeCun][AGI][Choe] AGI vs. Human-Level AI
- [Deepmind][AGI] A Generalist Agent (GATO) by Google Deepmind
- [NLP][LM] Meta AI Opensources their lanauge model OPT-175B
- [Book] Neuroscience and Philosophy
- A mathematical model unlocks the secrets of vision
- [Google][NLP][LM] Pathways Language Model (PaLM) by Google
- [Lab Seminar][Tool][Choe] Three Ingredients for Becoming a Proficient Tool User
- A Survey on Intrinsic Motivation in Reinforcement Learning
- [Tool][Book][Choe] Animal Tool Use
- [Action][Tool] Getting a grip on hand function
- [Action][Choe] Masked Visual Pre-Training for Motor Control
- Self-training with unlabeled data to improve generalization
- [Evolution][Module] Evolution of intelligence: Modular Cognition
- [Time][Buonomano][Choe][Lab Seminar] The human brain and the nature of time
- [Choe] My library books
- [Kahneman][Choe] Daniel Kahneman, on Adversarial Collaboration
- [Consciousness][Choe] Muscularity of Mind
- [Fridman][Zuckerberg][Meta] Lex Fridman interviews Mark Zuckerberg
- [Philosophy] Critique of Bayesianism by Mark Bickhard
- [Choe] My philosopher.ai questions answered
- [LeCun] A grand research vision by Yann LeCun. Lots of perception/action!
- Gradients without backpropagation
- [Notice][Choe] Renovated web page launched!
- [Tutorial] Definitive guide to embedding
- Schmidt Futures Foundation: New AI funding!
- Computer scientists prove that big neural networks are better
- What neural signals trigger motion/action?
- AI and ML Salaries Drop
- [DeepMind] AlphaCode - human level competitive coder!
- [Tool] Virtual Tools Game at MIT
- Meta's Data2Vec: works for speech, vision, and text
- Less is more: Simplify your data for better performance
- [Interview] Lex Fridman interviews Yann Lecun
- [Lab Seminar][Body][Choe] Proprioception and the importance of spatial intelligence / bodily experience
- [Google] Jeff Dean on ML, 2021 and beyond
- [SfN] How AI is deepening our understanding of the brain
- [RIKEN][Choe] Free energy principle explains the brain?
- [Consciousness][Choe] Machine consciousness and Buddhist philosophy
- Introduction to explainable AI
- Bias-variance dilemma in ML and neuroscience
- What does it mean for AI to understand: Melanie Mitchell
- [Choe] My revised paper: Meaning vs. information, prediction vs. memory, and question vs. answer
- 2021
- [Mind][Choe] Mental phenomena don't map into the brain as expected
- [Tool][Choe] Crows understand the concept of tool value!
- [Cognition][Choe] Ordering information into sequences improves cognitive performance
- [fMRI][GPT3] AI mimicking the brain on its own
- [Philosophy][Choe] Mechanisms of meaning
- What does it mean for a machine to Understand
- [Rufin Van Rullen] Deep Learning and Global Worlspace theory
- Even the simplest brain circuit is hard to understand
- [Tutorial] Complex valued neural networks
- [Evolution][Choe] Simulated AI: how mind and body evolved together
- Gradients are not all you need
- [Lab Seminar] The Ingredients of Real-World Robotic Reinforcement Learning
- [NeurIPS][Choe] 2021 accepted papers
- [DeepMind] Reinforcement learning lectures w/ UCL
- [Tutorial] on graph neural networks
- [Lab Seminar] Neural heterogeneity promotes robust learning
- [Tutorial][Choe] A recipe for training neural networks
- [Hinton] Representing part-whole hierarchies
- [Mind] On minimal cognition: Pamela Lyon
- Neural networks solving partial differential equations?
- [Mind][Choe] Need for a Copernican shift to understand the mind: Pamela Lyon
- [AGI] David Deutsch on AGI: inteview
- Learning function from structure in neuromorphic networks
- [Facebook][Choe] Self-supervised learning at Facebook
- Diversity in neural response leads to faster learning
- AI is no match for the quirks of human intelligence
- Dream and its relation to preventing overfitting
- AI Boom and Bust: History and prospect
- [Oudeyer][Choe] Exciting talk on developmental artificial intelligence
- [Consciousness] Consciousness in plants
- [Lab Seminar] Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor.
- Deep learning's diminishing returns
- Lifelong reinforcement learning!!
- [GPT] GPT4 to be 500X larger than GPT3
- Foundation models for AI?
- [Lab Seminar][CNN] Activation atlases
- The neuroscience of hierarchical reinforcement learning
- [Lab Seminar] Buzsaki's interview in Neuron 2016
- [Interview] Lex Fridman interviews Rodney Brooks!
- Neural scaling laws!
- [DeepMind] Deepmind opensourced Perceiver IO
- A universal law of robustness
- [CNN] Do vision transformers see like CNNs?
- Foundation Models - shared by Chul Sung
- [Philosophy][Kording][Choe] Philosophical understanding of representation in neuroscience
- [Kording] Deep learning framework for neuroscience
- [Kording] 6502 chip, neuroscience, and Donkey Kong! by Konrad Kording et al.
- Policy gradients incorporating the fugure
- NYU Deep Learning lectures
- [Deepmind] Perceiver IO
- [Consciousness] Role of dopamine in consciousness
- Creation of abstract thoughts in the brain
- Mouse prefrontal cortex learns rules for visual categorization
- How we learn: Why the brain is better than the machine? - Stanislas Dehaene
- Diversity is all you need: Learning skills without a reward function
- [OpenAI] Robitics team disbanded
- [Oudeyer] Causal reinforcement learning using observational and interventional data
- Reward is enough
- [Lab Seminar][Neural code][Choe] Good decisions require more than information
- What kind of qualities do top ML papers value?
- [RL] Fully interactive indoor environment for RL research
- Self-supervised learning
- [CVPR] Embodied AI workshop
- [Lab Seminar][Stanley] Neuroevolution - Ken Stanley's work
- [Psychology] Psychology of artificial superintelligence
- Autoencoders for outlier detection
- Neural circuits underlying novelty seeking behavior (curiosity)
- [VR][Gaze] How human gaze behaves differently in VR
- [Book] Deep learning theory book
- [Consciousness] Representational drift in primary olfactory cortex
- [ICRA] Yann LeCun's self-supervised learning and world models talk
- [ICLR] Geometric deep learning
- [Grounding][Choe] Grounding natural language meaning based on physical interaction with the world - Yejin Choi lab
- [NSF][Choe] Workshop on analyzing neural circuits
- [Evolution] Neuroevolution workshop
- Deep physical neural networks
- Fast and slow learning of recurrent independent mechanisms
- [Prediction][Choe] Fly brain constantly predicts change in the environment
- [Body][Choe] Third Thumb: Human augmentation and plasticity of the brain
- [CNN] CNN vs. Transformers - which is more like human vision?
- Train Keras model with genetic algorithms
- [Octopus] Film: My octopus teacher
- [Tutorial] BERT, explained in sketches
- Network dissection: Semantic meaning of CNN/GAN units
- [NEAT][Choe] How single-cell organisms can reach its life's goal with such simple machinary!
- [Embodied] Curious representation learning for embodied intelligence
- [ICML] Barlow twins: self-supervised method to train joint-embedded architectures
- [Lab Seminar] Online virtual training in soft actor-critic for autonomous driving
- Why AI is harder than we think, by Melanie Mitchell
- Pieter Abbeel interview: Reinforcement learning for industrial AI
- PRECOG: prediction conditioned on goals in visual multi-agent settings
- [Lab Seminar] Curiosity-driven Exploration by Self-supervised Prediction
- [Stanley][Choe] Open-endedness in AI: Ken Stanley
- The brain rotates memories to save them from new sensations: mouse study, catastrophic forgetting
- [CNN] Use shallow network to triage samples that lead to shallow features
- [Lab Seminar] We’ll never have true AI without first understanding the brain
- CPU algorithms faster than on GPU : Rice university
- [Neuralink] Monkey plays MindPong via brain machine interface
- Waymo CEO steps down
- Convert transformers to RNN to reduce size
- [Lab Seminar] Rainbow Memory: Continual Learning with a Memory of Diverse Samples
- [RL] Stored embedding for more efficient reinforcement learning
- The aftermath of Element AI's sell off to a US company
- Continual learning paper: rainbow memory
- Why AI cannot make themselves smarter?
- More interesting work on transformers
- [Motor] Interesing neuroscience research on motor system and machine learning
- [Lab Seminar] Using Eye Gaze to Enhance Generalization of Imitation Networks to Unseen Environments
- Attention is not all you need: huge inductive biases in self-attention based models
- Reward prediction and decoding the decision making process in the brain
- [RL] Crash course on reinforcement learning
- [Lab Seminar] Attention is all you need
- Pretrained transformers as universal computation engines
- [Lab Seminar] Transformer is All You Need: Multimodal Multitask Learning with a Unified Transformer
- [LeCun] Yann LeCun on self-supervised learning for vision
- [Hawkins][Choe] Jeff Hawkins' new book on the brain: A Thousand Brains
- [Consiousness][Choe] Consciousness prior - Bengio group
- [Stanley] Open-ended AI, by Ken Stanley
- Minecraft environment for open-ended AI
- Transformers are all you need
- [Stanley][OpenAI][RL] Reinforcement learning in games
- [Lab Seminar] If deep learning is the answer, what is the question?
- [Grounding][Choe] Grounding spatial topology and metric regularity through sensorimotor learning
- Analyzing how BERT encodes grammatical features
- [GoogleAI] automated model search
- [Body][Choe] Importance of proprioception
- [Saxe][Choe] Andrew Saxe on analyzing simple neural networks to understand neural networks better
- [Tool][RL] Deep reinforcement learing for tool use
- [Cognition][Insect] Solitary bees can solve novel tasks
- [Body] How bumble bees perceive the spatial layout of their surrounding relative to their body
- [GAN] Using GAN to generate super mario brothers game levels
- Evolution + learning + embodied intelligence
- Causal entropic forces: An intriguing paper from 2013
- Liquid machine learning system adapts to changing conditions
- [NeurIPS] AI designs lesson plans for itself
- Symposium on explanation in neuroscience and AI
- Importance of understanding behavior, in neuroscience
- How mirroring up the architecture of the brain is speeding up AI learning
- [Prediction][Choe] Learning the predictability of the future
- 90% Top-1 accuracy in ImageNet!
- [RL] Predictin the visual attention of drivers via RL
- AI and Brain Science symposium: videos
- What Neural Networks Playing Video Games Teach Us About Our Own Brains
- [OpenAI] DALL-E: creating images from text
- [NEAT] Deep neuroevolution better than Deep nnet? -- Ken Stanley
- [KAIST] Visual number sense in untrained deep neural net
- [Book] Intro to probabilistic machine learning
- 2020
- [Time] Hippocampus not only encodes space, it ecodes time!
- [Gary Marcus][Choe] Insights for AI from the human mind
- Evaluating agents without rewards
- [Choe] AI debate 2 : some interesting take aways
- [Self][Choe] The information theory of individuality
- Why we need to study behavior to understand the brain
- [NeurIPS] Faster, more efficient alternatives to backprop
- [Samsung] Head researcher wants human-AI interactions to be multimodal : Sebastian Seung
- If deep learning is the answer, what is the question?
- Accurate neural network computer vision without the black box
- [RL] Deep RL architecture combines pre-learned skills to create new sets of skills on the fly
- AI debate 2
- Do wide and deep neural networks learn the same thing?
- [HBP][Choe] A documentary on the 1 billion Euro European brain project
- Visualization of self-attention
- [Cauaslity] Causal discovery in physical systems from videos
- [Grounding] Action concept grounding network for semantically consistent video generation
- AI that designs its own robots
- [Lab Seminar] High-frequency Component Helps Explain the Generalization of CNN
- [ICML] Meta learning tutorial
- [Lab Seminar] Neural circuit policies enabling auditable autonomy
- [Robot] Neurorobots as a means toward neuroethology and explainable AI
- [Lab Seminar] [Choe] Time, Brain, and Neural Networks
- Next generation of AI
- 100+ AI use cases
- Biologically inspired neural networks for self-driving card
- AI algorithm learning with practically no data
- State of AI report 2020
- [LeCun] Implicit rank-minimizing auto-encoder
- [Lab Seminar] Towards Practical Hierarchical Reinforcement Learning for Multi-lane Autonomous Driving
- Use of Transformers in vision!
- Image augmentation is all you need
- Slot attention-based classifier for explainable image recognition
- [Lab Seminar] Few-Shot Learning with Global Class Representations
- [Lab Seminar] Towards Universal Representation Learning for Deep Face Recognition
- [Consciousness] How to give AI consciousness!!!
- [Buzsaki][Choe] The brain from inside out - by Gyorgy Buzsaki!
- Neural signal statistics and sensory gain control - shared by Chul Sung
- [Philosophy] Oxford's free course on critical reasoning for beginners
- [Lab Seminar] [Li] Synthesizing Light Field From a Single Image with Variable MPI and Two Network Fusion
- [Neuralink] Brain chip presentation by Elon Musk!!
- [Neuralink] Neuralink brain implant chip
- [Philosophy][Choe] Philosopher AI + GPT 3 = Awesome!!
- [Meaning][Lake][Choe] Word meaning in minds and machines!!
- [Choe] Math genealogy project!
- Using ears, not just eyes, improves robot perception
- Metric learning reality check
- [Causality] Causal entropic forces - a very interesting paper from 2013!!
- Can this explain why deep learning works so well?
- Contrastive self-supervised learning
- Hack your sensors - Neosensory challenge
- [Faecbook] Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Object files and schemata: Factorizing declarative and procedural knowledge in dynamical systems
- [Choe] Thoughts on learning motor primitives
- Learning to learn!
- [Buzsaki] Mystery of the brain, shared by Qing Wan
- [CVPR] Workshop on continual learning
- [Prediction] To make sense of the present, brains may predict the future
- [Choe] My lecture on the limitations of deep learning and how to overcome them
- [Prediction][Choe] Probing emergent semantics in predictive agents via question answering
- [AGI] The AGI conference 2020!
- The unreasonable effectiveness of deep learning in AI
- Deep learning state of the art 2020 - MIT
- [LeCun] Wisdom by Yann LeCun
- [Uber] Massive lay off at Uber AI
- If deep learning is the answer, what is the question?
- [BBC] Bumble bee plays soccer!
- Self-supervised learning
- Neighborhood component analysis
- Distilled BERT
- Symbolic mathematics using deep learning
- [Choe] My Ph.D. student Han Wang graduated!
- [BBC] An organutan using a saw to cut tree branches!
- [Kording][Koene] Randal Koene interviews Konrad Kording!
- IKEA furniture assembly environment!
- Open problems in artificial life
- [Robot] Robots with insect brains!! - by Barbara Webb
- [Mind][Choe] Why your brain is not a computer!
- [Facebook] Evolutionary optimization platform by Facebook
- [OpenAI] OpenAI microscope - visualization tool set, shared by Khuong Nguyen
- [Wolfram] Stephen Wolfram explains everything with his latest theory
- [Deepmind] Agent57 plays all 57 Atari 2600 games - DQN
- [Clune] Open-ended reinforcement learning
- [Memory][Choe] Bayesian superorganism III: externalized memories facilitates ...
- Evolutionary population curriculum!
- [Choe] Arxiv-sanity: excellent resource for finding and organizing papers
- [Grounding] A survey on symbol emergence
- Autonomous driving company shuts down
- [Sejnowski][Choe] The unreasonable effectiveness of deep learning in AI - Terry Sejnowski
- [Choe] My chapter in the INNS 30th anniversary book
- Training neural nets faster on CPUs than GPUs
- [RL] Deep RL in the real world, shared by Khuong Nguyen
- [Gestalt][Choe] Insight learning, a paradigm to make deep learning better?
- Gradient free learning?
- [Uber AI] Generative teaching network (GTN)
- [DeepMind] new RL papers - HT Khuong Nguyen
- [Gary Marcus][Choe] Next decade in AI
- [Allen Institute] Visual cortical neurons behave not like we thought
- Facebook Group Mirror
- 2019
- Old postings - not from the Facebook group
- Editable Neural Networks
- Training-Free Artificial Neural Networks
- [Uber] EvoGrad: Lightweight library for gradient-based evolution
- [MIT+IBM] Neurosymbolic AI
- Discovering Neural Wirings
- Learning the Depths of Moving People by Watching Frozen People
- [Book] Possible Minds: Twenty-Five Ways of Looking at AI
- [Newton] Newton's eye poke experiment!
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
- [Sony] Neural Network Libraries by Sony : Nabla
- [Hopfield] Unsupervised learning by competing hidden units
- [Classic] A critique of pure vision, by Churchland, Ramachandran, and Sejnowski
- [Stanford] Weak Supervision: A New Programming Paradigm for Machine Learning
- How the Brain Links Gestures, Perception and Meaning
- GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
- [Embodiement] Embodied Multimodal Multitask Learning
- Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research
- How do Mixture Density RNNs Predict the Future?
- The Evolved Transformer
- [Robot] Self-aware machines : Robot that can imagine itself
- [Oudeyer] Curiosity driven exploration of learned disentangled goal spaces
- Slimmable Neural Networks
- Reconciling modern machine learning and the bias-variance trade-off
- An Empirical Study of Example Forgetting during Deep Neural Network Learning
- 2018
- [BBS] Building machines that learn and think like people
- Speaker Recognition from Raw Waveform with SincNet
- Structured Pruning of Neural Networks with Budget-Aware Regularization
- Joint Neural Architecture Search and Quantization
- Dataset Distillation
- [Uber][Stanley] Go-Explore solves Montezumas Revenge
- Sampling Can Be Faster Than Optimization
- [Choe] Artificial Intelligence in the Age of Neural Networks and Brain Computing
- Massively Parallel Hyperparameter Tuning
- FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks
- You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
- [Kording] Towards learning-to-learn
- How deep is deep enough? - Optimizing deep neural network architecture
- ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
- [OpenAI] Reinforcement Learning with Prediction-Based Rewards
- [IBM] Fabric for deep learning (FfDL)
- [Olfaction][Choe] On the nose: Sissel Tolaas is a star in the world of smells.
- [Curiosity] Honda teams up with MIT and others to develop curious AI
- [Curiosity] Large-scale study of curiosity-driven learning
- Adaptive nodes enrich nonlinear cooperative learning beyond traditional adaptation by links
- Unsupervised Learning via Meta-Learning
- Recurrent World Models Facilitate Policy Evolution
- Resilient Computing with Reinforcement Learning on a Dynamical System: Case Study in Sorting
- [Google Brain] AI needs a little bit of Robot AI
- The Elephant in the Room
- [Deepmind] Neuroscience-inspired AI
- GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
- Advancing AI by exploring the minds of children
- Neural Architecture Search: A Survey
- Accelerating Deep Neural Networks with Spatial Bottleneck Modules
- [Facebook] Hash-tag label based image data set
- [Google][RL] Open source RL framework
- [Polani][Intrinsic] Changing the Environment Based on Empowerment as Intrinsic Motivation
- Lucid: tools for research in neural network interpretability
- [McCulloch+Pitts] What the Frog's Eye Tells the Frog's Brain - 1959 paper
- Large-Scale Study of Curiosity-Driven Learning
- L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data
- OBOE: Collaborative Filtering for AutoML Initialization
- [Evolution] Backprop Evolution
- [Philosophy] Andy Clark: Embodied mind
- Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks
- Simulating Action Dynamics with Neural Process Networks
- Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks
- [Kording] Toward an integration of Deep Learning and Neuroscience
- Eigenvector continuation with subspace learning
- 3D image reveals hidden neurons in fruit-fly brain
- DARTS: Differentiable Architecture Search
- HyperNetworks
- [Evolution] Convolution by Evolution: Differentiable Pattern Producing Networks
- [RL] Why RL is flawed?
- [Evoluition] Co-evolution and AI
- Taskonomy: Disentangling Task Transfer Learning
- Gradient Acceleration in Activation Functions
- [CNN] An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
- A Simple Method for Commonsense Reasoning
- SparseNet: A Sparse DenseNet for Image Classification
- Path-Level Network Transformation for Efficient Architecture Search
- [Theory] Probabilities over What?
- Playing hard exploration games by watching YouTube
- Neural language representations predict outcomes of scientific research
- Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students
- Understanding Convolutional Neural Network Training with Information Theory
- Taskonomy: Disentangling Task Transfer Learning
- [OpenAI] AI and compute: Moore's law?
- Compressibility and Generalization in Large-Scale Deep Learning
- A Taxonomy for Neural Memory Networks
- Substitute Teacher Networks: Learning with Almost No Supervision
- [Deepmind] Prefrontal cortex as a meta-reinforcement learning system
- How Robust are Deep Neural Networks?
- Is neuromorphic AI the next big thing?
- Learning Awareness Models
- Hierarchical Representations for Efficient Architecture Search
- Adversarial Network Compression
- The Kanerva Machine: A Generative Distributed Memory
- Exploring manifolds using pretrained CNNs for unsupervised tuning
- [Uber][Stanley] Differentiable Plasticity: A New Method for Learning to Learn
- [Dev] Keras Templates
- [Schmidhuber] World models
- How to find the hyperparameters more efficiently
- [Grounding] Unsupervised textual grounding
- [Deepmind][Prediction] Memory and prediction based approach for POMDP problems: 3D maze
- Speeding up learning with importance sampling
- Not All Samples Are Created Equal: Deep Learning with Importance Sampling
- [Risto] From Nodes to Networks: Evolving Recurrent Neural Networks
- [BAIR] Composable Deep Reinforcement Learning for Robotic Manipulation
- Neural plasticity only occurs near the major trunks near the soma
- [Deepmind] Understanding deep learning through neuron deletion
- [Lipson] Self-replicating neural networks: Neural Network Quine
- How accurate is your AI?
- Composing policies learned from RL!
- [Sentient] Evolutionary search for RNNs
- Investigating Human Priors for Playing Video Games
- Saving samples in external memory during training with context-based lookup
- [DeepMind] Machine Theory of Mind
- [BAIR] Diversity is All You Need: Learning Skills without a Reward Function
- Why Artificial Intelligence Like AlphaZero Has Trouble With the Real World
- Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
- Model compression via distillation and quantization
- Inverting The Generator Of A Generative Adversarial Network (II)
- Generating Plans that Predict Themselves
- [ULCA] Deep learning workshop
- Neural Relational Inference for Interacting Systems
- Efficient Neural Architecture Search via Parameter Sharing
- Visual Data Augmentation through Learning
- The Matrix Calculus You Need For Deep Learning
- Regularized Evolution for Image Classifier Architecture Search
- Neural Algebra of Classifiers
- Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent
- [DiCarlo] To Advance Artificial Intelligence, Reverse-Engineer the Brain
- PRNN: Recurrent Neural Network with Persistent Memory
- Learning to Prune Filters in Convolutional Neural Networks
- [Deepmind] Learning explanatory rules from noisy data
- Meta-Learning with Adaptive Layerwise Metric and Subspace
- In-network Neural Networks
- An Overview of Machine Teaching
- [Tactile] SenseNet: 3D Objects Database and Tactile Simulator
- Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
- Generating Neural Networks with Neural Networks
- Data Augmentation by Pairing Samples for Images Classification
- Compressing Deep Neural Networks: A New Hashing Pipeline Using Kac's Random Walk Matrices
- Theory of Deep Learning III: explaining the non-overfitting puzzle
- ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
- [Karpathy] Software 2.0!!
- ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks
- [Stanley][Evolution] Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
- Visualizing the Loss Landscape of Neural Nets
- [Gary Marcus] Deep learning: A critical appraisal
- [Brooks] Rodney Brooks: predictions on AI
- [Intrinsic][Choe] Disentangling the independently controllable factors of variation by interacting with the world
- 2017
- Ray RLLib: A Composable and Scalable Reinforcement Learning Library
- Unifying Map and Landmark Based Representations for Visual Navigation
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning
- Im2Flow: Motion Hallucination from Static Images for Action Recognition
- [Grounding] Generalized Grounding Graphs: A Probabilistic Framework for Understanding Grounded Commands
- AI2-THOR: An Interactive 3D Environment for Visual AI
- High performance ultra-low-precision convolutions on mobile devices
- FearNet: Brain-Inspired Model for Incremental Learning
- Experiential, Distributional and Dependency-based Word Embeddings have Complementary Roles in Decoding Brain Activity
- Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
- [CNN] Karpathy's visualization of CNN representations
- A Berkeley View of Systems Challenges for AI
- Neural Map: Structured Memory for Deep Reinforcement Learning
- MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
- Learning by Asking Questions
- [GAN] Generalizing GAN: A Turing perspective
- Data Distillation: Towards Omni-Supervised Learning
- [BAIR] MAML : Model Agnostic Meta Learning
- [Lab Seminar] Cassie Bub - Analysis of Time-Delayed Neural Networks in Ball Catching Task
- [Lab Seminar] [Nowak][Lee][Choe] Knife-Edge Scanning Microscopy: Towards Full-Scale Analysis of the Cerebrovasculature System of the Whole Mouse Brain
- [Lab Seminar] Understanding and Self-Organization
- [Lab Seminar] [Evolution] Evolving Deep Neural Networks
- [Lab Seminar] [RNN][LeCun] Tracking the World State with Recurrent Entity Networks
- [Lab Seminar] [Reams][Choe][Tool] Emergence of tool construction in an articulated limb controlled by evolved neural circuits
- [Lab Seminar] Edge.org annual questions
- 2016
- [Lab Seminar] Essay by Christoph von der Malsburg 'AI: Tinned human thought?'
- [Lab Seminar] [Nguyen][Choe] Explanation of the perceptual oblique effect based on the fidelity of oculomotor control during saccades
- [Lab Seminar] Toward an integration of deep learning and neuroscience
- [Lab Seminar] [Graves][Memory] Hybrid computing using a neural network with dynamic external memory
- [Lab Seminar] [Intrinsic] Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation
- [Lab Seminar] Machine learning needs rich feedback for AI teaching: Monash professor
- [Lab Seminar] Cognitive Offloading Does Not Prevent but Rather Promotes Cognitive Development
- [Lab Seminar] Mirrors and feelings: Have you seen the actors outside?
- [Lab Seminar] [Freeman] A neurobiological interpretation of semiotics: meaning, representation, and information
- [Lab Seminar] [Clune] Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
- [Lab Seminar] [Stigmergy] Stigmergy as a universal coordination mechanism II: Varieties and evolution
- [Lab Seminar] [Nowak][Choe] Knife-Edge Scanning Microscopy for in silico Study of Cerebral Blood Flow: from Biological Imaging Data to Flow Simulations
- [Lab Seminar] When machines think and feel
- [Lab Seminar] The minority report: some common assumptions to reconsider in the modeling of the brain and behavior
- [Lab Seminar] The IEEE CIS CDS newsletter, dialog section on representational redescription.
- [Lab Seminar] [IIT][Consciousness] The Problem with Phi: A Critique of Integrated Information Theory
- [Lab Seminar] Edge.org annaul questions
- 2015
- [Lab Seminar] IEEE CIS Newsletter on Autonomous Mental Development
- [Lab Seminar] [Beer] Connecting a connectome to behavior: an ensemble of neuroanatomical models of C. elegans klinotaxis
- [Lab Seminar] Topological basis for the robust distribution of blood to rodent neocortex
- [Lab Seminar] The Future of the Brain: Essays by the World's Leading Neuroscientsts
- [Lab Seminar] [Stanley] Improving evolvability through novelty search and self-adaptation
- [Lab Seminar] On simplicity and complexity in the brave new world of large-scale neuroscience
- [Lab Seminar] [Consciousness][Block] Consciousness, big science, and conceptual clarity
- [Lab Seminar] Computational rationality: A converging paradigm for intelligence in brains, minds, and machines
- [Lab Seminar] [Parulkar][Choe] Autonomous Grounding of the Optical Flow Detectors in a Simulated Visuomotor System of the Fly
- [Lab Seminar] The mouse that roared: neural mechanisms of social hierarchy
- [Lab Seminar] [BMI] The brain–computer interface cycle
- [Lab Seminar] Self-taught learning: transfer learning from unlabeled data
- [Lab Seminar] Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups
- [Lab Seminar] [RL] Human-level control through deep reinforcement learning
- [Lab Seminar] [Self][Body] Interoceptive inference, emotion, and the embodied self
- [Lab Seminar] Machines that learn to segment images: a crucial technology for connectomics
- [Lab Seminar] Exploration versus exploitation in space, mind, and society
- [Lab Seminar] [RL] Reinforcement learning: Computational theory and biological mechanisms
- [Lab Seminar] Edge.org 2015 question center
- 2014
- [Lab Seminar] Vectorization of optically sectioned brain microvasculature: Learning aids completion of vascular graphs by connecting gaps and deleting open-ended segments
- [Lab Seminar] Place cells, grid cells, and the brain's spatial representation system
- [Lab Seminar] [RL] An automated measure of MDP similarity for transfer in reinforcement learning
- [Lab Seminar] Brain-machine interfaces: past, present and future
- [Lab Seminar] Cortical control of arm movements: a dynamical systems perspective
- [Lab Seminar] [Li][Choe][Yoo][Tool] Emergence of Tool Use in an Articulated Limb Controlled by Evolved Neural Circuits
- [Lab Seminar] [Consicousness] A Mechanistic Theory of Consciousness
- [Lab Seminar] [Koch] Hacking the Soul
- [Lab Seminar] Edge.org World Question Center
- [Lab Seminar] [Sporns] Complex brain networks: graph theoretical analysis of structural and functional systems
- [Lab Seminar] The neuron classification problem
- [Lab Seminar] [Choe] Brain Connectivity Mapping. IJCNN tutorial 2013
- [Lab Seminar] [Action] Developmental perception of the self and action
- [Lab Seminar] [RL] Reinforcement learning transfer using a sparse coded inter-task mapping
- [Lab Seminar] Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration
- 2013
- [Lab Seminar] The Brain's Connective Core and Its Role in Animal Cognition
- [Lab Seminar] [DiCarlo] Untangling invariant object recognition
- [Lab Seminar] [Schmidhuber] First experiments with PowerPlay
- [Lab Seminar] [Causality] Causal Entropic Forces
- [Lab Seminar] [Consciousness] The Inevitable Contrast: Conscious versus Unconscious Processes in Action Control
- [Lab Seminar] [Consciousness] How to make a robot that is conscious and feels
- [Lab Seminar] Representing task context: proposals based on a connectionist model of action
- [Lab Seminar] [Time] Time and brain: neurorelativity: The chronoarchitecture of the brain from the neuronal rather than the observer's perspective
- [Lab Seminar] [Yoo][Choi][Choe] Motor map development
- [Lab Seminar] Differential retinal origins of separate anatomical channels for pattern and motion vision in rabbit
- [Lab Seminar] How to Think Like Leonardo Da Vinci
- [Lab Seminar] Dan Pink on Motivation - TED talk
- [Lab Seminar] Emotions: From Brain to Robot
- 2012
- [Lab Seminar] What is the computational goal of the neocortex
- [Lab Seminar] Critique of Pure Vision
- [Lab Seminar] Data sharing in neuroimaging research
- [Lab Seminar] [Evolution] Evolving Reusable Neural Modules
- [Lab Seminar] Pattern recognitionin bees
- [Lab Seminar] [Sarma][Choe] Salience in orientation-filter response measured as suspicious coincidence in natural images
- [Lab Seminar] Fast and accurate retinal vasculature tracing and kernel-isomap-based feature selection
- [Lab Seminar] Fast cell detection in high-throughput imagery using gpu-accelerated machine learning
- [Lab Seminar] An Environment Model for Nonstationary Reinforcement Learning
- [Lab Seminar] Edge.org Question Center 2012: What is your favorite deep, elegant, or beautiful explanation
- 2011
- [Lab Seminar] ./genlab
- [Lab Seminar] [Evolution] Evolution of the brain and intelligence
- [Lab Seminar] Cortical substrates for exploratory decisions in humans
- [Lab Seminar] Fast Delineation and Visualization of Vessels in 3-D Angiographic Images
- [Lab Seminar] Exploitation vs. exploration
- [Lab Seminar] Pavlov's AI – What did it mean?
- 2010
- [Lab Seminar] [RL] Reinforcement learning in finite MDPs: PAC Analysis
- [Lab Seminar] [Yang][Choe] Interactive editing tools for EM image analysis
- [Lab Seminar] A novel tracing algorithm for high throughput imaging Screening of neuron-based assays
- [Lab Seminar] Waxholm space
- [Lab Seminar] On vergence control model
- [Lab Seminar] Ecological expected utility and the mythical neural code
- [Lab Seminar] Singularity and Slow Convergence of the EM algorithm for Gaussian Mixtures
- [Lab Seminar] From bottom-up visual attendion to robot action learning
- [Lab Seminar] Multiagent learning
- [Lab Seminar] [Mann][Choe] Prenatal vs. postnatal developoment
- [Lab Seminar] [Choi][Choe] Manifold integration with markov random walk
- 2009
- [Lab Seminar] An Energy Minimization Approach to the Data Driven Editing of Presegmented Images/Volumes
- [Lab Seminar] Predicting student performance
- [Lab Seminar] [Han][Choe] Fast and Accurate Retinal Vasculature Tracing and Kernel-Isomap-based Feature Selection
- [Lab Seminar] [Park][Choe] Tactile or Visual?: Stimulus Characteristics Determine Receptive Field Type in a Self-Organizing Map Model of Cortical Development
- [Lab Seminar] [Kuipers] Towards the Application of Reinforcement Learning to Undirected Developmental Learning
- 2008
- [Lab Seminar] Natural Image Statistics and Efficient Coding
- [Lab Seminar] Stereo Pseudo 3D Rendering for Web-Based Display of Scientific Volumetric Data
- [Lab Seminar] Modular Neuroevolution for Multilegged Locomotion
- [Lab Seminar] [Tactile] Tactile dominance in speeded discrimination of textures
- [Lab Seminar] [Choe][Kwon] Internal state predictability as an evolutionary precursor of self-awareness and agency
- [Lab Seminar] [Haptics] Geometrical haptic illusions: the role of exploration in the Muller-Lyer, vertical-horizontal, and Delboeuf illusions
- [Lab Seminar] Decision making, impulsivity and time perception
- [Lab Seminar] Stochastic Models, Estimation, and Control
- [Lab Seminar] [Robot][Semantics] Natural Semantics for a Mobile Robot
- [Lab Seminar] [Oliva] Natural scene categorization from conjunctions of ecological global properties
- [Lab Seminar] Mathematical Representation of the Vascular Structure and Applications
- 2007
- [Lab Seminar] Simultaneous Truth and Performance Level Estimation(STAPLE): An Algorithm for the Validation of Image Segmentation
- [Lab Seminar] [Evolution] Towards an Empirical Measure of Evolvability
- [Lab Seminar][Motor][Kuniyoshi] Early Motor Development from Partially Ordered Neural-body Dynamics: Experiments with a Cortico-spinal-musculo-skeletal Model
- [Lab Seminar] [Mikula] Internet-Enabled High-Resolution Brain Mapping and Virtual Microscopy
- [Lab Seminar] [BBS][Evolution] Archaeology and Cognitive Evolution
- [Lab Seminar] [DiCarlo] Spatial and Temporal Structure of Receptive Fields in Primate Somatosensory Area 3b: Effects of Stimulus Scanning Direction and Orientation
- [Lab Seminar][Polani] Empowerment: A Universal Agent-Centric Measure of Control
- [Lab Seminar] [Seth][Edelman] Distinguishing Causal Interactions in Neural Populations
- [Lab Seminar][Sporns] The Human Connectome: A Structural Description of the Human Brain
- [Lab Seminar] Prediction of external events with our motor system: towards a new framework
- [Lab Seminar] The skill of seeing: beyond the sensorimotornext term account?
- [Lab Seminar] When is Scene Identification Just Texture Recognition?
- [Lab Seminar] Projecting Sensations to External Objects: Evidence from Skin Conductance Response
- [Lab Seminar] Involuntary Motor Activity in Pianists Evoked by Music Perception
- [Lab Seminar] Interpolating Subdivision for Meshes with Arbitrary Topology
- [Lab Seminar] Small-World Brain Networks
- [Lab Seminar][Sporns] Mapping Informatinon Flow in Sensorimotor Networks
- [Lab Seminar] Independent component analysis of natural images sequences yield spatiotemporal filters similar to simple cells in primary visual cortex
- 2006
- [Lab Seminar] [Bongard] Resilient Machines Through Continuous Self-Modeling
- [Lab Seminar] Rapid Automated Tracing and Feature Extraction from Retinal Fundus Images Using Direct Exploratory Algorithms,
- [Lab Seminar] Active vision and receptive field development in evolutionary robots
- [Lab Seminar] A model of the ventral visual system based on temporal stability and local memory
- [Lab Seminar] [Tool] Tool-use changes multimodal spatial interactions between vision and touch in normal humans
- [Lab Seminar][Consciousness] Thinking as simulation of behaviour: an associationist view of cognitive function
- [Lab Seminar] Feedback dynamics and cell function: Why systems biology is called systems biology
- [Lab Seminar] [Claxton] Wise up: the challenge of life long learning
- [Lab Seminar] [Haggard] Conscious intention and motor cognition
- [Lab Seminar] [Humphrey] How to solve the mind-body problem
- [Lab Seminar] [Lashley] The Problem of Serial Order in Behaviour
- [Lab Seminar] Modeling Sensorimotor Learning with Linear Dynamical Systems
- [Lab Seminar] Abnormalities in the awareness of action
- [Lab Seminar] Thalamus papers by Mumford
- [Lab Seminar] Semantic integration of XML heterogenneous data sources
- [Lab Seminar] Learning sparse codes with a mixture-of-gaussians prior
- [Lab Seminar] The dynamics of active categorical perception in an evolved model agent
- [Lab Seminar] Language within our grasp
- [Lab Seminar] Rapid visual-motion integration deficit in autism
- [Lab Seminar] A topographical method for the development of neural networks for artificial brain evolution
- [Lab Seminar] Intrinsically Motivated Reinforcement Learning
- 2005
- [Lab Seminar] The emergence of a 'Language' in an evolving population of neural netowrks
- [Lab Seminar] Is there something out there? Inferring space from sensorimortor dependencies
- [Lab Seminar] Motion-based autonomous grounding: Inferring external world properties from internal sensory states alone
- [Lab Seminar] Half a Centry of Research on the Stroop Effect: An Integrative Review
- [Lab Seminar] Spatio-temporal predictive neural coding found in Orientation flash-lag effect
- [Lab Seminar] Clark (1997), The Dynamical Challenge
- [Lab Seminar] Muscularity of Mind: Towards an Explanation of the Transition from Unconscious to Conscious
- [Lab Seminar][Tool] Role of tool use in cognitive development
- [Lab Seminar] Learning of action through adaptive combination of motor primitives
- [Lab Seminar] Shared neural control of attentional shifts and eye movements
- [Lab Seminar] Spike-timing dependent plasticity and orientation flash-lag effect
- [Lab Seminar] Computational Role of Disinhibition in Brain Function
- [Lab Seminar] Comparison of motor-based versus visual representations in object recognition tasks
- [Lab Seminar] Cangelosi (2000): symbol grounding
- [Lab Seminar] John Weng: Autonomous Mental Development
- [Lab Seminar] Interactivist perception
- [Lab Seminar] Leyton: Symmetry/Asymmetry in Memory
- [Lab Seminar] Flash lag effect ; Dynamic synapses
- [Lab seminar][Action] Action
- [Lab Seminar] Fully distributed representations
- 2004
- [Lab Seminar] Learning from uninterpreted experience in the SSH
- [Lab Seminar] Is there something out there? Inferring space from sensorimotor dependencies
- [Lab Seminar] Bergson and cognitive science
- [Lab Seminar] A bayesian model of imitation in infants and robots
- [Lab Seminar] Organization, development and function of complex brain networks
- [Lab Seminar] A biologically plausible model of associative memory which uses disinhibition rather than long-term potentiation
- [Lab Seminar] Optimal smoothing in visual motion perception
- [Lab Seminar] Conscious thought as simulation of behaviour and perception
- [Lab Seminar] Extending ESP with temporal properties
- [Lab Seminar] The Metaphorical Brain 2: Neural Networks and Beyond
- [Lab Seminar] Texture segmentation in 2D vs. 3D: Did 3D developmentally precede 2D?
- [Lab Seminar] The Man Who Mistook His Wife for a Hat and Other Clinical Tales
- 2003
- [Lab Seminar] Neural correlates of perceptual learning: a functional mri study of visual texture discrimination.
- [Lab Seminar] Bayesian modeling of human concept learning
- [Lab Seminar] The current relevance of merleau-ponty’s phenomenology of embodiment
- [Lab Seminar] Visual analogy in problem solving
- [Lab Seminar] Aspects and extensions of a theory of human image understanding
- [Lab Seminar] An introduction to the visual system
- [Lab Seminar] Representations in the brain.
- [Lab Seminar] When vision is not sight: dissociations between vision and action
- [Lab Seminar] Mirror neurons and imitation learning as the driving force behind ``the great leap forward'' in human evolution
- [Lab Seminar] The knife-edge scanning microscope
- [Lab Seminar] Introduction: A bayesian formulation of visual perception
- [Lab Seminar] Detecting salient contours using orientation energy distribution