Neural Nets

Function approximators.

Learning summary statistics 2022-11-24

Gradient flows infinitesimal optimization 2020-01-30 – 2022-11-02

Deep learning as a dynamical system 2018-08-13 – 2022-10-30

The edge of chaos Computation, evolution, competition and other past-times of faculty 2016-12-01 – 2022-10-30

Pytorch #torched 2018-05-04 – 2022-10-23

Generative art with language+diffusion models 2022-09-16 – 2022-10-20

Neural tangent kernel 2020-12-09 – 2022-10-14

Multi-objective optimisation 2021-07-14 – 2022-10-10

Automatic programming 2016-10-14 – 2022-10-07

Statistics and ML in python 2015-04-27 – 2022-10-06

Neural denoising diffusion models Denoising diffusion probabilistic models (DDPMs), score-based generative models, generative diffusion processes, neural energy models… 2021-11-11 – 2022-09-24

Score matching 2021-11-11 – 2022-09-23

Ensemble Kalman methods for training neural networks Data assimilation for network weights 2022-09-20

Gradient descent, first-order, stochastic a.k.a. SGD, as seen in deep learning 2020-01-30 – 2022-09-05

Causal inference in highly parameterized ML 2020-09-18 – 2022-09-02

Transformer networks The transformer-powered subtitle recommendation for this article was “Our most terrifyingly effective weapon against the forces of evil is our ability to laugh at them.” 2017-12-20 – 2022-08-23

Technological singularities Incorporating hard AI take-offs, game-over high scores, the technium, deus-ex-machina, deus-ex-nube, nerd raptures and so forth 2016-12-01 – 2022-08-10

Neural nets with implicit layers Also, declarative networks, bi-level optimization and other ingenious uses of the implicit function theorem 2020-12-08 – 2022-08-09

Nonparametrically learning dynamical systems 2018-08-13 – 2022-08-06

Learning Gamelan 2016-04-05 – 2022-08-05

Neural net attention mechanisms On brilliance through selective ignorance 2017-12-20 – 2022-08-05

Neural learning for spatiotemporal systems 2020-09-16 – 2022-07-28

Gradient descent, Newton-like 2019-02-05 – 2022-07-25

Overparameterization in large models Improper learning, benign overfitting, double descent 2018-04-04 – 2022-05-27

Machine learning and statistics in Julia 2019-11-27 – 2022-05-27

Graph neural nets 2020-09-16 – 2022-05-18

Implementing neural nets 2016-10-14 – 2022-05-18

Probabilistic neural nets Bayesian and other probabilistic inference in overparameterized ML 2017-01-11 – 2022-04-07

Reservoir Computing 2022-03-28

Generative flow 2022-03-07

Differentiable learning of automata 2016-10-14 – 2022-02-19

Neural nets for “implicit representations” 2021-01-21 – 2022-02-01

Neural nets with basis decomposition layers 2021-03-09 – 2022-02-01

Here’s how I would do art with machine learning if I had to 2016-06-06 – 2022-02-01

Running neural nets backwards 2022-01-29

Garbled highlights from NeurIPS 2021 2021-11-05 – 2021-12-15

Gradient descent, Newton-like, stochastic 2020-01-23 – 2021-12-09

Ensembling neural nets Monte Carlo 2020-12-14 – 2021-11-25

Convolutional neural networks 2017-11-10 – 2021-11-21

Neural nets for “implicit representations” 2021-01-21 – 2021-11-16

Deep generative models 2020-12-10 – 2021-11-11

Random neural networks 2017-02-17 – 2021-10-12

Regularising neural networks Generalisation for street fighters 2017-02-12 – 2021-09-24

Economics of automation When to the robots come for my job? 2021-09-20

Recurrent neural networks 2016-06-16 – 2021-09-06

Neural network activation functions 2017-01-12 – 2021-08-02

Learning summary statistics 2020-04-22 – 2021-07-15

Multi-task ML 2021-07-14

ML on small devices Putting intelligence on chips small enough to be in disconcerting places 2016-10-14 – 2021-07-13

Tensorflow The framework to use for deep learning if you groupthink like Google 2016-07-11 – 2021-07-07

ML Koans Passing through the NAND-gate 2021-06-23

Infinite width limits of neural networks 2020-12-09 – 2021-05-11

Compressing neural nets pruning, compacting and otherwise fitting a good estimate into fewer parameters 2016-10-14 – 2021-05-07

ML benchmarks and their pitfalls On marginal efficiency gain in paperclip manufacture 2020-08-16 – 2021-04-13

Memory in machine learning 2021-03-03 – 2021-03-03

Statistical mechanics of statistics 2016-12-01 – 2021-01-06

Why does deep learning work? Are we in the pocket of Big VRAM? 2017-05-30 – 2020-12-14

Garbled highlights from NeurIPS 2020 2020-09-17 – 2020-12-11

Big data ML best practice 2020-09-16 – 2020-09-21

Dimensionality reduction Wherein I teach myself, amongst other things, feature selection, how a sparse PCA works, and decide where to file multidimensional scaling 2015-03-22 – 2020-09-11

Neural nets Designing the fanciest usable differentiable loss surface 2016-10-14 – 2020-09-09

Learning of manifolds Also topological data analysis; other hip names to follow 2014-08-19 – 2020-06-23

Deep fakery 2020-06-15

Teaching computers to write music 2016-06-06 – 2020-03-25

Learnable indexes and hashes 2018-01-12 – 2020-02-18

Gradient descent, Higher order 2019-10-26

Entity embeddings 2017-04-01

Garbled highlights from NIPS 2016 2016-12-05 – 2017-02-03

Pattern machine 2011-06-27 – 2015-11-24