Braindumps
My current zettle. Comments and opinions are my own. No guarantees on correctness.
Research Topics
Misc Topics
Workflow Ideas
Books
Graph
Index
-
ADAM
-
Action Potential (Neuron)
-
Active Learning
-
Actor Critic
-
Additive noise models
-
Additivity
-
Afferent Codes
-
Analysis
-
Anatomy
-
Aperiodic
-
Artificial Intelligence
Aliases:
- AI
-
Asymetric Shapley Values
-
Atari
Aliases:
- ALE Arcade Learning Environment
-
Autocorrelation
Aliases:
- serial correlation
-
Auxiliary Tasks
-
Backpropagation Through Time
-
Backpropagation
-
Bases (Linear Algebra)
Aliases:
- basis
-
Behavior-Suite
-
Behavioral Science
-
Behaviorism
-
Bellman Equation
-
Bellman Optimality Equation
-
Biased Competition
-
Bijective
-
Binocular rivalry
-
Bootstrapping (statistics)
-
Brain
-
Braindump
-
Calculus
-
Category Theory
-
Cauchy Criterion
-
Causal Model
-
Causal State Representations
-
Causal Sufficiency
Aliases:
- causally sufficient
-
Causality
-
Charles S. Peirce
-
ChatGPT
-
Classification
-
Cognitive Revolution
-
Cognitive Science
-
Common Cause principle
-
Company
-
Compute Canada
-
Conditional Shapley Values
-
Connectionist Network
-
Continuous
-
Control Theory
-
Converges
-
Correlation
-
Critterbot
-
Cross-Entropy
-
Curiosity
-
Current Learning Objectives
-
Deep Learning
-
Deep Reinforcement Learning
Aliases:
- DRL
-
DeepMind Lab
-
Determinant
-
Developmental Reinforcement Learning
-
Diagonal Matrix
Aliases:
- rectangular diagonal matrix
-
DiffEQ
-
Dimensionality Reduction
-
Dirac Delta Function
-
Discrete
-
Dopamine
-
Dopaminergic Neurons
-
Dot Product
-
Duality
-
Dynamic Programming
-
Efferent Codes
-
Efficient Coding
-
Eigendecomposition
-
Eigenvalues and Eigenvectors
Aliases:
- eigenspaces
- eigenvector
- eigenvalues
-
Elementary Differential Equations and Boundary Value Problems
-
Empirical Risk Minimization
-
Environments
-
Ergodic
-
Experience Replay
Aliases:
- ER buffer
-
Free-Energy Principle
-
Function Space
-
GPT3
-
GPT4
-
GRU
-
Gaussian Elimination
-
General Value Functions
Aliases:
- GVF
-
Gradient Descent
Aliases:
- GD
- Batch Gradient Descent
-
Gradients over vector fields
Aliases:
- jacobian
- curl
- divergence
-
Hadamard product
-
Helmholtz Sign Theory
-
Hermann von Helmholtz
-
Hierarchical Predictive Coding
Aliases:
- Predictive Coding
-
Higher Order Operators
Aliases:
- second derivative
- hessian
- laplace operator
-
Hilbert Space
-
Hoeffding Inequality
-
Homogeneity
-
How to Take Smart Notes with Org-mode
-
Hypothesis
-
Ideomotor Principle
-
Image
-
Inbox
-
Incentive Salience
-
Independence of mechanism and input
-
Independent Shapley Values
-
Infimum and Supremum
-
Injective
-
Inner Product Space
-
Integral Transform
-
Intelligence
-
Interview Review Material
-
Invariance theorem
-
Isomorphism
-
Job Hunt
-
John Hopfield
-
KL Divergence
-
Kernel Function
-
Kolmogorov Complexity
-
LSTM
-
Lagrange multipliers
-
Laplace Transform
-
Large Language Models
-
Linear Algebra and its Applications
-
Linear Algebra
-
Linear Map
Aliases:
- Linearity Linear Transform
- Linear Function
-
Linear Programming
-
Linear Regression
-
Machine Learning
-
Markov Chain
-
Markov Decisions Process
-
Math
-
Matrices
Aliases:
- Matrix
-
Matrix Addition
-
Matrix Adjugate
Aliases:
- Cofactor Matrix
-
Matrix Definiteness
Aliases:
- positive definiteness
- negative definiteness
-
Matrix Factorizations
Aliases:
- matrix factorization
- matrix decomposition
-
Matrix Inverse
Aliases:
- inverse
-
Matrix Operations
-
Matrix Product
Aliases:
- Matrix Hadamard Product
- Matrix Kronecker Product
-
Matrix Trace
-
Matrix Transpose
Aliases:
- Matrix Conjugate Transpose
- conjugate transpose
- transpose
-
Maximum Likelihood Estimation
Aliases:
- MLE
- maximum likelihood estimator
-
Meta-Learning
-
Metric Space
-
Model-based RL
-
Morphism
-
Mountain Car
-
Neural Network
Aliases:
- ANN
-
Neurons
-
Neuroscience
-
Neurotransmitter
-
Normal Matrix
-
Note-Taking
-
Off-policy Reinforcement Learning
-
OpenAI
-
Optimization
-
Optimizers
-
Order Theory
-
Ordinary Least Squares
Aliases:
- OLS
-
Org Roam
-
POMDP
-
PSR
-
Partially Ordered Set
-
Peirce Semiotic
-
People
-
Perception
Aliases:
- perceptual system
-
Perpendicular Distance
-
Philosophy
-
Policy Improvement
-
Policy
Aliases:
- Policies
-
Pragmitism
-
Predictive Knowledge
-
Predictive Processing
-
Preimage
-
Pretraining for Reinforcement Learning
-
Principle Component Analysis
Aliases:
- PCA
-
Probability Theory
-
Probability via Expectations
-
Psychology
-
Puddle World
-
Python
-
Radical Behaviorism
-
ReLU Activation
-
Recurrent Neural Network
Aliases:
- RNN
-
Recursive Shapley Values
-
Reinforcement Learning in the Brain
-
Reinforcement Learning
-
Reinforcement Learning: An Introduction
-
Representation
-
Reproducibility in Science
Aliases:
- Reproducible
-
Resampling
-
Reward Prediction-Error Hypothesis of Dopamine
Aliases:
- RPEH
-
Reward
-
Rich Sutton
-
Richard Ernest Bellman
-
Richard Feynman
-
Richness of functional causal models
-
Rosenbrock function
-
SVD
-
Self-supervised Learning
-
Semi-supervised Learning
-
Semiotic
Aliases:
- Sign Theory
-
Shapley Values
-
Sigmoid Function
-
Single variate derivatives
Aliases:
- derivative
-
Special types of matrices
-
Stationary Point
Aliases:
- singular points
- extrema
- critical point
- inflextion point
- minima
- maxima
-
Statistics
-
Stochastic Gradient Descent
Aliases:
- SGD
-
Stochastic Processes
-
Subbasis
-
Subgradients
Aliases:
- subderivative
-
Sufficient Statistic
-
Supervised Learning
-
Support Vector Machines
Aliases:
- SVMs
- SVM
-
Surjective
-
Taylor Series Expansion
Aliases:
- Taylor series
- Taylor expansion
-
Temporal Difference Learning
-
The Causal Markov condition
-
The Causal Minimality Condition
-
The Faithfulness Condition
-
The Gradient Operator
Aliases:
- gradient
-
The Representational Theory of Mind
Aliases:
- RTM
-
Theory
-
Thinking
-
Topology
-
Triangle Matrix
Aliases:
- upper triangular matrix
- lower triangular matrix
-
Types of Learning
-
Unitary Matrix
Aliases:
- complex unitary matrix
- orthongonal matrix
-
Unsupervised Learning
-
Upperbound 2023
-
Value Function
-
Vector Space
-
Visual System
-
Zettelkasten method
-
Zuckerman Institute
-
badia2020agent57: Agent57: Outperforming the Atari Human Benchmark
-
barreto2018successor: Successor Features for Transfer in Reinforcement Learning
-
bouthillier2019unreproducible: Unreproducible Research is Reproducible
-
bubic2010prediction: Prediction, cognition and the brain
-
byrd2019what: What is the Effect of Importance Weighting in Deep Learning?
-
chandar2019nonsaturating: Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
-
chung2014empirical: Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
-
clark2013whatever: Whatever next? Predictive brains, situated agents, and the future of cognitive science
-
cogprints316: Facing Up to the Problem of Consciousness
-
colombo2014deep: Deep and beautiful. The reward prediction error hypothesis of dopamine
-
dayan1993improving: Improving Generalization for Temporal Difference Learning: The Successor Representation
-
gonzalez-soto2019reinforcement: Reinforcement Learning is not a Causal problem
-
goodman2016what: What Does Research Reproducibility Mean?
-
goudreau1994firstorder: First-order versus second-order single-layer recurrent neural networks
-
henderson2018deep: Deep Reinforcement Learning That Matters
-
hochreiter1997long: LONG SHORT-TERM MEMORY
-
hopfield1985neural: ``Neural'' computation of decisions in optimization problems
-
huang2011predictive: Predictive Coding
-
jaderberg2017reinforcement: Reinforcement Learning with Unsupervised Auxiliary Tasks
Aliases:
- UNREAL
-
james2004learning: Learning and Discovery of Predictive State Representations in Dynamical Systems with Reset
-
kearney2019making: Making Meaning: Semiotics Within Predictive Knowledge Architectures
-
kostas2019asynchronous: Asynchronous Coagent Networks: Stochastic Networks for Reinforcement Learning without Backpropagation or a Clock
-
lehnert2017advantages: Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning
-
littman2002predictive: Predictive Representations of State
-
liu2018breaking: Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
-
machado2018revisiting: Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
-
mnih2014recurrent: Recurrent Models of Visual Attention
-
mnih2016asynchronous: Asynchronous Methods for Deep Reinforcement Learning
-
mohamed2019monte: Monte Carlo Gradient Estimation in Machine Learning
-
niv2009reinforcement: Reinforcement learning in the brain
-
prinz1990common: A Common Coding Approach to Perception and Action
-
rao1999predictive: Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects
-
roy2018editorial: Editorial: Representation in the Brain
-
russell2004history: History of Western Philosophy
-
scholkopf2019causality: Causality for Machine Learning
-
schwarzer2021pretraining: Pretraining Representations for Data-Efficient Reinforcement Learning
-
singh2003learning: Learning Predictive State Representations
-
soga2009predictive: Predictive and postdictive mechanisms jointly contribute to visual awareness
-
spratling2017review: A review of predictive coding algorithms
-
sternberg2016cognitive: Cognitive Psychology
-
stock2004short: A short history of ideo-motor action
-
subramanian2020approximate: Approximate information state for approximate planning and reinforcement learning in partially observed systems
-
sutskever2011generating: Generating text with recurrent neural networks
-
sutton1988learning: Learning to predict by the methods of temporal differences
-
sutton2011horde: Horde: A Scalable Real-time Architecture for Learning Knowledge from Unsupervised Sensorimotor Interaction
-
sutton2020john: John McCarthy's definition of intelligence
-
synofzik2013experience: The experience of agency: an interplay between prediction and postdiction
-
vanhasselt2015learning: Learning to Predict Independent of Span
-
veeriah2019discovery: Discovery of Useful Questions as Auxiliary Tasks
-
wang2017learning: Learning to reinforcement learn
-
white2015developing: Developing a predictive approach to knowledge
-
white2017unifying: Unifying Task Specification in Reinforcement Learning
-
wu2016multiplicative: On Multiplicative Integration with Recurrent Neural Networks
-
zhang2021learning: Learning Causal State Representations of Partially Observable Environments