Active inference
Everyone is talking about active inference but no one implementing it. Right? This is what makes me think that everyone is talking about it…
Read more...Big topics A-Z
Adaptive Resonance Theory
All ART models Fresh article where Grossberg critisicizes back propagation and deep learning. And related interview that planned to be a…
Read more...Bidirectional Associative Memories
BAM can link together data of different types. Associations... From one side the model requires to use bipolar patterns - arrays of -1 and…
Read more...Brain map
Phenotypic variation of transcriptomic cell types in mouse motor cortex (paper). Scientist got neurons from different layers and regions and…
Read more...Cascade Correlation Neural Networks
Neural networks with biologically plausible accounts of neurogenesis they start with a minimal topology (just input and output unit) and…
Read more...Cognitive Architecture
ACT-R CLARION LIDA Soar (code)
Read more...Convolutional Neural Networks
A long time ago, I was thinking about systems that perceive only video input. But the more I read about image processing, the more I get a…
Read more...Diffusion models
Also: Stable Diffusion and 3D Tutorials https://lilianweng.github.io/posts/2021-07-11-diffusion-models/ Another diffusion tutorial https…
Read more...Generative Adversarial Networks (GANs)
Unsupervised image classification with GAN Resources Awesome list of many papers about GAN networks and links to the code Tips and tricks to…
Read more...Hopfield Networks
It probably started in 1982. Full crash course about Hopfiled networks. Train Predict Full notebook on AI sandbox More resources An example…
Read more...Hyperdimensional computing
About the research I got one little thing: spiking neurons are a part of Neural Engineering Framework. It’s a stupid name. It defines some…
Read more...Long Short-Term Memory
Main paper PDF stacking lstms https://stats.stackexchange.com/questions/163304/what-are-the-advantages-of-stacking-multiple-lstms intro to…
Read more...Markov decision processes
Neural networks, classification and clusterization algorithms are considered to be intelligent as far as they are part of Artificial…
Read more...Multi agent systems
Intuitively, intelligence and consciousness seem to be highly correlated. The smartest animals we know of are also the ones that show the…
Read more...Neural coding
Temporal Coding Radix Encoding
Read more...Recurrent Neural Networks
ANN should have notion of time. RNN can do it Event sequence prediction How to encode time in ANN? With the help of another ANN that will…
Read more...Reinforcement Learning
Roadmap Tabular (Lecture 20, Huggingface course, develop the thing from scratch) DQN (DQN Paper and implement something better than any…
Read more...Reservoir Computing
TODO ;)
Read more...Spiking Neural Networks
Better than any words, you can get an idea how SNNs work from this animation. But here's a downside: ...in order to reach accuracy of its…
Read more...Last reviews
All reviews here
Discovery of question
by RL agent formulated as general value functions
(2019) - by Vivek Veeriah et al
Beaver escaping from prison
Reward id not Necessary: How to Create a Compositional Self-Preserving Agent for Life-Long Learning
(2022) - by Thomas J. Ringstrom
Enabling Brain-Inspired Processors
Through Energy-Efficient Delayed Feedback Reservoir Computing Integrated Circuits
(2020) - by Yang Yi
Firing patterns in the adaptive exponential integrate-and-fire model
in the adaptive exponential integrate-and-fire model
(2008) - by Naud R, Marcille N, Clopath C, Gerstner W.
Temporal Coding in Spiking Neural Networks
with Alpha Synaptic Function: Learning with Backpropagation
(2020) - by Comsa et al