Search
Search
Dark mode
Light mode
Folder: general
1131 items under this folder.
A–Z
Recent
A critique of pure learning and what artificial neural networks can learn from animal brains
A Simple Framework for Contrastive Learning of Visual Representations
A Simple Modification in CMA-ES Achieving Linear Time and Space Complexity
A7
abelian group
absolute homogeneity
absolute value
absolutely convergent
abstraction
abstraction layers
access consciousness
accumulation point
activation function
activation space
actor critic
adaptation
adaptive computation time
adaptive levin search
addition
Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
adjacency list
adjacency matrix
advantage
advice
agency
agent
agential material
AGI Unbound with Joscha Bach - Consciousness and the future of Intelligence
AGI-25 Conference - Machine Consciousness - Cyberanimist Hypothesis - Joscha Bach
agnosticism
AI-GAs - AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
Ai4Science Alphaxiv 19-09-25 - Jeff Clune
AIXI
Alan Turing
aleatoric uncertainty
algebra
algorithm
Algorithm Discovery With LLMs - Evolutionary Search Meets Reinforcement Learning
algorithmic complexity
alienation
ALIFE 2025
alignment
An Explanation of In-context Learning as Implicit Bayesian Inference
anacrontab
analytic distinction
angular frequency
animism
Anthropic Interpretability - Understanding how AI models think
Anti-Dühring
antisymmetric
appendage to the machine
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
ARC-NCA - Towards Developmental Solutions to the Abstraction and Reasoning Corpus
archimedean property
art
artem kirsanov
artificial collective intelligence
artificial intelligence
artificial life
artificial neural network
associative memory
astrocyte
asymptote
Asynchronicity in Neural Cellular Automata
attention (general)
attention (ML)
attention economy
Attention Residuals
attractor
augmented matrix
automatic curriculum learning
Automating the Search for Artificial Life with Foundation Models
autoregressive
AVL-Tree
B7
backpropagation through time
backward causality
basis
batch gradient descent
batch normalization
Bayes Theorem
bayesian inference
bayesian neural network
bayesian statistics
bayesianism
beauty
Bellman Equation
bernoulli
bernoulli inequality
bff
bias
bias-variance tradeoff
bijective
bilinear map
binary operation
binomial coefficient
binomial distribution
bio-electricity
Bio-Inspired Plastic Neural Networks for Zero-Shot Out-of-Distribution Generalization in Complex Animal-Inspired Robots
biology
Bishop Berkeley
black-box optimization
Bolzano-Weierstrass
boolean algebra
Bootstrap your own latent - A new approach to self-supervised Learning
bootstrapping
boredom
borel set
Born to Learn - the Inspiration, Progress, and Futureof Evolved Plastic Artificial Neural Networks
bounded
bourgeois
bourgeois democracy
brain
Brain Criticality - Optimizing Neural Computations - Artem Kirsanov
BraiNCA - brain-inspired neural cellular automata and applications to morphogenesis and motor control
brute fact
C7
CA-NEAT - Evolved Compositional Pattern Producing Networksfor Cellular Automata Morphogenesis and Replication
cached thought
can we understand the universe
Capital as Artificial Intelligence
capitalism
cardinality
Carmack UpperBound25
cartesian product
catastrophic forgetting
categories
category error
category theorey
cauchy distribution
cauchy sequence
cauchy-schwarz inequality
causal
causal attention
causal structure
cell
cellular automata
Central Limit Theorem
central moment
central pattern generator
chain rule of probability
Challenges in High-dimensional Reinforcement Learning with Evolution Strategies
change
chebyshev inequality
Chesterton's fence
childhood amnesia
church-turing thesis
Class Struggle In The Roman Republic
Classical sorting algorithms as a model of morphogenesis - Self-sorting arrays reveal unexpected competencies in a minimal model of basal intelligence
classification
closure
cma-es
codomain
coefficient of variation
cofactor expansion
cognition
cognitive chunking
cognitive light cone
cognitive load
cognitive map
coherence
cohesion
collective intelligence
Collective Intelligence for Deep Learning - A Survey of Recent Developments
column space
combinatorics
communicability
communication
Communism - The higher stage of communist society
commutative
comparison test
competing conventions problem
competition
completeness axiom
complex conjugate
complex number
complexification
complexity
composition
composition adds information
compositional pattern-producing network
computable
computation
Computation at the edge of chaos - Phase transitions and emergent computation
computational functionalism
computational irreducibility
computationalism
computronium
conditional independence
conditional probability
conditioning
congruence
congruence class
conjugate trick
connection cost
consciousness
Consciousness as a coherence-inducing operator - Consciousness is virtual
consciousness is self-reflexive attention
consciousness is social
conscription
conservative
constraint
constructivism
contingent
continual backpropagation
continuous
continuous extension
contrastive learning
Contribute to balance, wire in accordance - Emergence of backpropagation from a simple, bio-plausible neuroplasticity rule
convergence
Conversation between Josh Bongard, Atoosa Parsa, Richard Watson, and Michael Levin
Conversation with Nic Rouleau - Some thoughts on the mind as material, neuroscience, memory transfer, aging of cognition, and more
convex combination
convex function
convex set
Coordination Among Neural Modules Through a Shared Global Workspace
correlation
correlation matrix
cortical column
coset
cosine distance
cosine similarity
countable
countable additivity
counterfactual
coupling
covariance
covariance matrix
Crafter
creativity
credit assignment
crime
Critical Neural Cellular Automata
critical state
cross product
cross-attention
cross-entropy
cross-entropy loss
crossover
cultural evolution
culture
culture war
cumulative distribution function
curiosity
Curiosity-driven Exploration by Self-supervised Prediction
curse of dimensionality
Curt Jaimungal x Michael Levin and Joscha Bach - Collective Intelligence
cyber animism
cybernetics
cybersin
cycle-consistency
cyclic group
D7
Daniele Grattarola x MLST
darwin complete
Darwin Godel Machine - Open-Ended Evolution of Self-Improving Agents
das Kapital
Data-Efficient Reinforcement Learning with Self-Predictive Representations
DBSCAN
decision transformer
decision tree
degrwoth
democratic centralism
Der Linke Radikalismus - Die Kiniderkraknheit im Kommunismus
derivative
deskilling
determinant
developmental biology
developmental encoding
Developmental encodings promote the emergence of hierarchical modularity across very different mechanisms
diagonal matrix
dialectic
Dialectics of Nature
differentiability
Diffusion Models are Evolutionary Algorithms
DiLoCo
directed acyclic graph
discipline
discovery
discrete
Discussion between Elliot Murphy and Michael Levin 1
disjoint
disjoint union
distance
distribution-based
diversity
division
division of labor
Does Capital Dream of Artificial Labor
Does predictive coding have a future
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model
dollar
domain
dot product
DQN
Dream To Control - Learning Behaviours By Latent Imagination
DropConnect
dropout
DRY
dualism
dynamic
dynamic equilibrium
dynamic instability
dynamic stability
Dynamical robustness in complex networks - the crucial role of low-degree nodes
dynamical system
dynamical system with dynamical structure
dynamical-systems lens on neural networks
E(n)-equivariant Graph Cellular Automata
E7
eccentricity
echo state network
education
effective rank
eigenbasis
eigendecomposition
eigenspace
eigenvalue
elementary CA
elementary matrix
eligibility trace
elitism (selection)
Embracing curiosity eliminates the exploration-exploitation dilemma
emergence
emotions
empiricism
enactivism
Encoding innate ability through a genomic bottleneck
energy-based models
Energy-Based Transformers are Scalable Learners and Thinkers
ensembles
entropy
Entscheidungsproblem
epigraph
epistemic uncertainty
epistemology
epsilon greedy
epsilon neighbourhood
equivalence relation
equivariance
ES is more than just a traditional finite-difference approximator
ES-HyperNEAT
essentialism
euclidean space
euclidian geometry
euler's number
even numbers
evergreen notes
evidence lower bound
evolution
Evolution as Backstop for Reinforcement Learning
evolution strategies
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Evolution Strategies at Scale - LLM Fine-Tuning Beyond Reinforcement Learning
Evolution Strategies at the Hyperscale
Evolution through Large Models
evolutionary optimization
Evolutionary Optimization of Model Merging Recipes
Evolving Hierarchical Neural Cellular Automata
Evolving Neural Networks That Are Both Modular and Regular - HyperNeat Plus the Connection Cost Technique
Evolving Self-Assembling Neural Networks - From Spontaneous Activity to Experience-Dependent Learning
expected value
exploding gradients
exploration vs exploitation
exponential
exponential distribution
extended euclidian algorithm
F1-score
factor group
factorial
factorization
factorized representations enable compositional generalization
facts
false negative
false positive
fascism
fast weights
feedforward
few-shot learning
fibonacci
field (algebra)
field (physics)
fingerstyle
first order optimization
fisher information
focal loss
fourier series
fourier transform
free will
frequentism
frequentist inference
Friedrich Engels
frobenius norm
From Entropy to Epiplexity - Rethinking Information for Computationally Bounded Intelligence
function
function graph
functional programming
functionalism
fundamental theorem of algebra
G7
gaussian elimination
general intelligence
General intelligence requires rethinking exploration
general value functions
General-Purpose In-Context Learning by Meta-Learning Transformers
generalization
generalization error
Generative Adverserial Nets
genome
genomic bottleneck
geometric mean
geometric projection
geometric series
George Hotz
Giving Up Control - Neurons as Reinforcement Learning Agents
GLU
goal
Gödel Machine
golden ratio
good representations enable simple methods
gradient
gram matrix
graph
graph attention
Graph Attention Networks
graph convolutional network
graph neural network
graph rewriting automata
graph transformer
great man theory
Gricean pragmatics
grid cell
grokking
group
group normalization
Growing Artificial Neural Networks for Control - the Role of Neuronal Diversity
GRU
guessing the teacher's password
Guitar Chords
halting problem
hamming distance
harmonic mean
hashing
hasse-diagram
Heavy-tailed neuronal connectivity arises from Hebbian self-organization
hebbian learning
Heraklit
hessian
hierarchical
Hierarchical consciousness - the Nested Observer Windows model
Hierarchical Neural Cellular Automata
High-Dimensional Continuous Control Using Generalized Advantage Estimation
high-level structure and function of the brain
hill-climbing
hippocampal remapping
hippocampus
homogeneity
homomorphism
Hopfield Network
horner's method
How Attentive are Graph Attention Networks
How to build conscious machines
How Your Brain Organizes Information - Can We Build an Artificial Hippocampus - Artem Kirsanov
human nature
humor
Hymba - A Hybrid-head Architecture for Small Language Models
HyperAgents
HyperNCA - Growing Developmental Networks with Neural Cellular Automata
HyperNEAT
hypernetwork
hypothesis testing
idea
idealism
idempotence
identity matrix
iid
Illuminating search spaces by mapping elites
Ilya x Dwarkesh
image
Improving the Efficiency of Distributed Training using Sparse Parameter Averaging
in-context learning
inattentional blindness
inclusion-exclusion principle
incompleteness theorems
Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity
indefinite matrix
independent
index set
indexed family
indirect encoding
Indirectly Encoding Neural Plasticity as a Pattern of Local Rules
induction head
inductive bias
inference
infinity
information
information theory
initialization
injective
inner product
intelligence
intelligence is collective
interest is socially constructed
internal contradiction
internet
interval
intrinsic curiosity module
intrinsic motivation
Introduction to RL
intuition
invariance
invention requires iteration
inverse
inverse matrix
Is Curiosity All You Need - On the Utility of Emergent Behaviours from Curious Exploration
ising model
isolated point
isometry
isomorph
isotropic
isotropic distribution
isotropic gaussian
jax
jeffreys prior
jensen's inequality
JKU - Mathematics for AI 1
JKU - Mathematics for AI 1 Exercise Sheet 5
JKU - SAT solving
JKU study plan
joint distribution
k-means
k-NN
Karl Marx
Kenneth O. Stanley - Novel Opportunities in Open-Endedness at UCL DARK
kernel density estimation
keynsianism
KL-divergence
kolmogorov complexity
kronecker delta
kurtosis
KV-cache
L-infinity norm
L1 distance
L1 norm
L2 distance
L2 norm
lambda calculus
language
laplace transform
Large Memory Layers with Product Keys
latent space
latent variable
lateral enthrorhinal cortex
lateral inhibition
lattice
law of large numbers
law of total probability
layer normalization
learaning order shapes representation quality
learnable
learned projection
learning
learning and working should not be separate life phases
Learning Global Rules from Local Patches - Scaling Neural Cellular Automata Training
Learning Graph Cellular Automata
Learning to Act through Evolution of Neural Diversity in Random Neural Networks
Learning to See by Looking at Noise
LeCun Initialization
Leibniz criterion
lenin
life
likelihood
limit
limit point
Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization
line segment
linear algebra
linear least squares regression
linear map over concatenation
linear order
linear systems of equations
linear transformation
linear transformer
linearly independent
lipschitz continuity
liquid state machine
Literature and Revolution
LLM
locallity of behavior
LocoFormer
log-derivative trick
log-likelihood
log-sum-exp trick
logarithm
logic
logistic regression
lognormal distribution
Long Run - Redgum
long-context
long-tailed
looped transformer
loss
loss of plasticity
Loss of plasticity in deep continual learning
lottery ticket hypothesis
LSTM
luddite
machine
Machine Consciousness - From Large Language Models to General Artificial Intelligence - Joscha Bach
machine learning
malthusianism
Manolis Kellis
marginal likelihood
marginalization
markov chain
markov chain monte carlo
markov property
markov's inequality
marxist economics
Mastering Atari Games with Limited Data
Mastering Atari With Discrete World Models
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Mastering Diverse Domains through World Models
materialism
Materialism and Empirio-criticism
mathematics
matrix
matrix factorization
matrix minor
matrix multiplication
MDP
mean
mean absolute error
mean squared error
meaning of life
measure
mechanistic
mechanistic interpretability
mechanistic reductionism
medial enthrorhinal cortex
median
memorization bootstraps generalization
memorization is an active, interpretative process
memory
memory in transformers
memory token
Memory Transformer
message passing
meta learning
Meta Learning Backpropagation And Improving It
Meta-Learning Bidirectional Update Rules
Meta-Learning through Hebbian Plasticity in Random Networks
metacognition
MetaGenRL
metaphysics
metric
metric learning
metric tensor
michael levin
Michael Timothy bennet
mind
mindset
mini-batch gradient descent
minimum description length principle
Mish
mixed selectivity
Mixture of A Million Experts
mixture of gaussians
mode
mode connectivity
mode-seeking
model merging
Model Merging in Pre-training of Large Language Models
modular
moment (mathematics)
moment-generating function
momentum
monism
monoid
monotone
monte carlo dropout
Monte Carlo Gradient Estimation in Machine Learning
monte carlo method
monte carlo tree search
morality
morphogenesis
Motif - Intrinsic Motivation from Artificial Intelligence Feedback
movement
MPLP - Learning a Message Passing Learning Protocol
Multi-Agent Advantage Decomposition Theorem
Multi-Agent Reinforcement Learning is a Sequence Modeling Problem
multi-head attention
multi-head latent attention
multi-layer perceptron
multi-scale
multifractal
multiplication
multiset
multivariate gaussian distribution
mutation
n-tuple
naive bayes
natural evolution strategies
NEAT
negation of the negation
negative definite
negative log-likelihood loss
neighbourhood
neural branching factor
neural cellular automata
Neural cellular automata - applications to biology and beyond classical AI
Neural Cellular Automata for ARC-AGI
neural network
Neural Ordinary Differential Equations
Neuroevolution of Self-Interpretable Agents
neuron
neuron firing process
neuroscience
neutral element
niching
norm
normal distribution
normal subgroup
Normalization - Scaling - Standardization
notation
note-taking
Notes
novel
novelty search
null hypothesis
null sequence
null space
observer
observer-dependent
obsidian markdown features
occam’s razor
odds
offline learning
OMNI-EPIC - Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
On the Measure of Intelligence
On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent
online learning
ontology
open-ended
Open-Endedness is Essential for Artificial Superhuman Intelligence
Open-endedness via Models of human Notions of Interestingnes
operation
operator
optimization
optimizing a metric destroys it
options framework
order
ordered field
Organic Structures Emerging From Bio-Inspired Graph-Rewriting Automata
orthogonal
orthogonal complement
orthogonality thesis
orthonormal
orthonormal basis
outer product
overfit
p-value
pain
Paired Open-Ended Trailblazer (POET) - Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Palm Muting
pancomputational enactivism
pancomputationalism
pareto distribution
partial order
particle swarm optimization
partition
Pascal's triangle
pattern matching
permutation
permutation equivariance
permutation invariance
permutation matrix
persistence
perspective
persuasion
phase transition
phenomenal consciousness
physicalism
pivot
place cell
planaria
planned economy
planning
Plato
platonic space
Platonic Space discussion 3
platonism
play
poisson distribution
policy
policy gradient
policy gradient theorem
policy iteration
polynomial
population statistic
population-based
positive definite
posterior
postmodernism
potentiation
Power Chords
power law
power series
power set
PPO
pre-image
precision
preference-based RL
premature abstraction
PreNorm
pretraining
principles
prior
probability
probability density function
probability distribution
probability mass function
process ontology
product
productivity
program
program synthesis
prompt caching
proof by induction
pseudo inverse
punishment
pyhsical laws are invariances across observers
Q-learning
Q-value
quadratic loss
qualia
quality diversity
Quality-Diversity Methods for the Modern Data Scientist
quantity and quality
quantum randomness
Questioning Representational Optimism in Deep Learning - The Fractured Entangled Representation Hypothesis
Questions to Guide the Future of Artificial Intelligence Research
radian
random forest
random variable
random walk
rank
rank-1 matrix
ratio test
rational function
rational number
rational numbers are dense in the reals
rationality
real
real number
real symmetric matrix
realism
reality
Recurrent Action Transformer with Memory
Recurrent Independent Mechanisms
Recurrent Memory Transformer
reductionism
refactoring
reference frame
reflexive
regret
regularity
regularization
reification
REINFORCE
reinforcement learning
reinforcement learning from verifyable rewards
relation
relational metaphysics
relational quantum mechanics
reliability
ReLU
representation
representation collapse
reproduction
Requirements for self organization
reservoir computing
Reservoir Computing - A New Paradigm for Neural Networks
ResNet
resonance
Resynthesizing behavior through phylogenetic refinement
revenge
revolutionary optimism
Richard Sutton
RMS norm
RNN
RNNs are feedforward networks with shared weights
ROC curve
root
root test
roots of unity
rotation invariance
rotational symmetry
roulette wheel selection
row echelon form
row space
rule 110
sacrifice
sample efficiency
sample statistic
sampling
sandwich rule
SARSA
scalar field
scale-free
scaled dot product attention
scaling
scaling compute
scaling data
scaling intelligence
Scaling Latent Reasoning via Looped Language Models
scaling laws
scaling memory
scaling parameters
scaling time
science
scientific realism
score function
second moment
second moment matrix
selection
self
self-attention
self-aware
Self-Distillation Enables Continual Learning
self-organization
self-referential
self-similar
semantic stopsign
semigroup
sensitivity
sensitivity (model variance)
sentience
separation of mental and manual labor
sequence
sequent calculus
Sergey x Dwarkesh
series
set
set constraints, not objectives
set function
SGD
short-term memory
Should I stay or should I go now
sigma-scaled selection
sigmoid
Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity
simple vs easy
simulated annealing
singular value decomposition
skewness
skip connection
sleep
softmax
solipsism
solomnoff induction
songs to play or sing
space (mathematics)
span
sparse distributed memory
sparsity
Spatially embedded recurrent neural networks reveal widespread links between structural and functional neuroscience findings
speciation
specificity
spectral radius
spectral theorem
spherical distribution
Spinoza
spirit
spline
SPRING - Studying the Paper and Reasoning to Play Games
square matrix
squared ReLU
Stabilizing Transformers for Reinforcement Learning
standard deviation
standard normal distribution
standardization
StarGANv2-VC A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
state space model
state-value
stationary distribution
statistics
stem cell
stepping stone
stochastic universal sampling
Streaming Deep Reinforcement Learning Finally Works
streaming RL
stress
subgroup
subjectivity
subsequence
subsumption of labor
success story algorithm
sum
supervised learning
supgen
support
surjective
surprise
Sutton & Barto RL Book Notes
Sutton x Dwarkesh
SwiGLU
Swish
symbiogenesis
symmetric
symmetric group
symmetric matrix
synaptic plasticity
synchrony
synthetic data
system of generators
system-1 thinking
system-2 thinking
tail sum formula
TD Lambda
teach reasoning, not memorization
Technological Approach to Mind Everywhere (TAME) - an experimentally-grounded framework for understanding diverse bodies and minds
telescoping
temporal difference learning
TensorNEAT - A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies
TerraLingua - Emergence and Analysis of Open-endedness in LLM Ecologie
test
test-time compute
The Architecture of Complexity
the big bang
The Big World Hypothesis and its Ramifications for Artificial Intelligence
The Bitter Lesson
The Blessing of Dimensionality in LLM Fine-tuning - A Variance-Curvature Perspective
The Cortex and The Critical Point - Understanding The Power of Emergence
The extended mind
The Free Transformer
The History of Philosophy - A Marxist Perspective
The mean preference is a bad estimate of preferences.
The Platonic Representation Hypothesis
The Pretense of Knowledge - On the insidious presumptions of Artificial Intelligence
The scaling of goals from cellular to anatomical homeostasis - An evolutionary simulation, experiment and analysis
the second brain
The Sensory Neuron as a Transformer Permutation-Invariant Neural Networks for Reinforcement Learning
The Structure of Scientific Revolutions
The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games
The Unbearable Slowness of Being
The Work Capacity of Channels with Memory - Maximum Extractable Work in Percept-Action Loops
the wrong abstraction
theory of mind
theory of mind is mind
thoughts are thinkers
Titans - Learning to Memorize at Test Time
Too much efficiency makes everything worse - overfitting and the strong version of Goodhart's law
Toward Agents That Reason About Their Computation
Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs
Toy Models of Superposition
Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Training Language Models via Neural Cellular Automata
transformer
Transformer Squared - Self-Adaptive LLMs
transformer-xl
transformers in RL
transitive
translation invariance
transpose
triangle inequality
triangular matrix
trigonometric function
trotzki
TRPO
true positive rate
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
truth
TU-Wien ADM Übungen
turing machine
type
Ubiquity
unbounded
uncertainty
understanding
unit circle
unitary
universal approximation theorem
universal computation
Universal Transformers
universal turing machine
unobserved variable
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
unsupervised learning
upper confidence bound
use-value
utopian socialism
vacuum
valence
value function
value iteration
vanishing gradients
variance
variation
variational inference
vector
vector field
vector space
VICReg
virtual
virtualism
Vision Transformers Need Registers
VOYAGER - An Open-Ended Embodied Agent with Large Language Models
wanting
warumup stable decay schedule
Wasserstein GAN
we can transcend biologies constraints
weakness maximization
Weight Agnostic Neural Networks
weight space
What is Intelligence - What is Life
what role does discipline play in collective intelligence
Where RNNs all we needed
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization
Who are we now
why does anything exist
William James
wolfram code
wolfram physics
working memory
world model
worse is better
zero order optimization
zero-shot learning
ZFS
Zipf's law
