# machine_learning

Visualising probabilistic graphical models
Also related models, such as Neural nets
2018-03-29
– 2023-02-02Last-layer Bayes neural nets
Bayesian and other probabilistic inference in overparameterized ML
2017-01-11
– 2023-02-02Transformer 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
– 2023-02-02Implementing neural nets
2016-10-14
– 2023-01-27Quantified self
Instrumentation and analytics for body and soul.
2022-01-11
– 2023-01-22Automatic programming
2016-10-14
– 2023-01-15Variational message-passing algorithms in graphical models
Cleaving reality at the joint, then summing it at the marginal
2014-11-25
– 2023-01-12Factor graphs
2019-12-16
– 2023-01-12Goodhart’s Law
2019-12-22
– 2023-01-11Graph neural nets
2020-09-16
– 2022-12-19Physics-informed neural networks
2019-10-15
– 2022-12-09Deep sets
invariant and equivariant functions
2022-11-24
– 2022-12-08Machine learning for physical sciences
Turbulent mixing at the boundary between two disciplines with differing inertia and viscosity
2017-05-15
– 2022-12-07Practical text generation and writing assistants
2019-01-08
– 2022-12-06Density ratio tricks
2022-12-06Nonparametrically learning dynamical systems
2018-08-13
– 2022-12-06Adverse advice selection
2022-01-25
– 2022-11-15Interaction effects and subgroups are probably what we want to estimate
2022-01-25
– 2022-11-06Deep learning as a dynamical system
2018-08-13
– 2022-10-30The edge of chaos
Computation, evolution, competition and other past-times of faculty
2016-12-01
– 2022-10-30Natural language processing software
Dave, although you took very thorough precautions in the pod against my hearing you, I could see your lips move.
2018-01-11
– 2022-10-23Generative art with language+diffusion models
2022-09-16
– 2022-10-20Neural tangent kernel
2020-12-09
– 2022-10-14Multi-objective optimisation
2021-07-14
– 2022-10-10Continuous and equilibrium probabilistic graphical models
2014-08-05
– 2022-10-10Φ-Flow
A modern python computational fluid dynamics library for ML research
2022-06-24
– 2022-10-04Learning graphical models from data
Also, causal discovery, structure discovery
2017-09-20
– 2022-10-01Voice transcriptions and speech recognition
2019-01-08
– 2022-09-25Ensemble Kalman methods for training neural networks
Data assimilation for network weights
2022-09-20Laplace approximations in inference
Lightweight uncertainties, especially for heavy neural nets
2021-07-28
– 2022-09-06Causal inference in highly parameterized ML
2020-09-18
– 2022-09-02Gaussian belief propagation
Least squares at maximal elaboration
2014-11-25
– 2022-09-01Scattering transforms
2022-03-16
– 2022-08-31Hydrology, applied
Rivers, aquifers and other wet things that can flood your house
2020-09-07
– 2022-08-30Neural PDE operator learning
2019-10-15
– 2022-08-29Machine learning for partial differential equations
2017-05-15
– 2022-08-29Elliptical belief propagation
Generalized least generalized squares
2022-08-22
– 2022-08-23Javascript machine learning
2017-01-13
– 2022-08-19Technological 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
– 2022-08-10Neural nets with implicit layers
Also, declarative networks, bi-level optimization and other ingenious uses of the implicit function theorem
2020-12-08
– 2022-08-09Ablation studies, lesion studies, and complex systems
2016-10-26
– 2022-08-06Causal inference on DAGs
Confounding! This scientist performed a miracle graph surgery intervention and you won’t believe what happened next
2016-10-26
– 2022-08-06Instumental variables and two stage regression
Confounding! This scientist performed a miracle graph surgery intervention and you won’t believe what happened next
2016-10-26
– 2022-08-06Neural net attention mechanisms
On brilliance through selective ignorance
2017-12-20
– 2022-08-05Neural learning for spatiotemporal systems
2020-09-16
– 2022-07-28Bayes linear regression and basis-functions in Gaussian process regression
a.k.a Fixed Rank Kriging, weight space GPs
2022-02-22
– 2022-07-27Integrated Nested Laplace Approximation
2021-07-28
– 2022-07-26Differentiable PDE solvers
2017-05-15
– 2022-07-20Learnable coarse-graining
Approximate meso-scale physics
2020-08-24
– 2022-07-13Multi fidelity models
Data-driven multi-scale sampling
2020-08-24
– 2022-07-12Hydrology, applied
Rivers, aquifers and other wet things that can flood your house
2020-09-07
– 2022-06-30Overparameterization in large models
Improper learning, benign overfitting, double descent
2018-04-04
– 2022-05-27Model interpretation and explanation
Colorizing black boxes
2016-09-01
– 2022-05-06(Discrete-measure)-valued stochastic processes
2019-10-10
– 2022-05-04Measure-valued stochastic processes
Moving masses
2020-10-16
– 2022-05-03Causal graphical model reading group 2022
Causal inference
2022-04-01
– 2022-04-29SLAM
Simultaneous Location and Mapping
2014-11-25
– 2022-04-28Vecchia factoring of GP likelihoods
Ignore some conditioning in the dependencies and attain a sparse cholesky factor for the precision matrix
2022-04-27Hierarchical models
DAGs, multilevel models, random coefficient models, mixed effect models, structural equation models…
2015-06-07
– 2022-04-21Model fairness
2018-11-29
– 2022-04-21Particle belief propagation
Graphical inference using empirical distribution estimates
2014-07-25
– 2022-04-08Particle Markov Chain Monte Carlo
Particle systems as MCMC proposals
2014-07-25
– 2022-04-08Probabilistic neural nets
Bayesian and other probabilistic inference in overparameterized ML
2017-01-11
– 2022-04-07Partition-valued random variates
2022-04-01Belief propagation
2014-11-25
– 2022-03-31Measure-valued random variates
Including completely random measures and many generalizations
2020-10-16
– 2022-03-30Reservoir Computing
2022-03-28Learning Gaussian processes which map functions to functions
2020-12-07
– 2022-02-25Learning with conservation laws, invariances and symmetries
2020-04-11
– 2022-02-25Moral calculus
2014-08-04
– 2022-02-19Differentiable learning of automata
2016-10-14
– 2022-02-19Neurons
Neural networks made of real neurons, in functioning brains
2014-11-03
– 2022-02-14Probabilistic graphical models
2014-08-05
– 2022-02-08Random graphical models
Causality in amongst confusion
2021-10-26
– 2022-02-07Neural nets for “implicit representations”
2021-01-21
– 2022-02-01Neural nets with basis decomposition layers
2021-03-09
– 2022-02-01Here’s how I would do art with machine learning if I had to
2016-06-06
– 2022-02-01Running neural nets backwards
2022-01-29Statistics and machine learning
2011-04-15
– 2022-01-27Learning on manifolds
Finding the lowest bit of a krazy straw, from the inside
2011-10-21
– 2022-01-26Causality via potential outcomes
Neyman-Rubin, counterfactuals, conditional treatment effects, and related tricks
2016-10-26
– 2021-12-10Convolutional subordinator processes
2021-03-08
– 2021-12-01Gaussian Processes as stochastic differential equations
Imposing time on things
2019-09-18
– 2021-11-25Ensembling neural nets
Monte Carlo
2020-12-14
– 2021-11-25Convolutional neural networks
2017-11-10
– 2021-11-21Neural nets for “implicit representations”
2021-01-21
– 2021-11-16External validity and dataset shift
Also transfer learning, learning under covariate shift, transferable learning, domain adaptation etc
2020-10-17
– 2021-11-03Probably Approximately Correct
2014-11-24
– 2021-10-27Neural music synthesis
2016-01-15
– 2021-10-14Random neural networks
2017-02-17
– 2021-10-12Missing data
Imputation, estimation despite etc
2021-10-07Regularising neural networks
Generalisation for street fighters
2017-02-12
– 2021-09-24Economics of automation
When to the robots come for my job?
2021-09-20Approximate Bayesian Computation
Posterior updates without likelihood
2020-08-25
– 2021-09-20Biological basis of language
2018-01-11
– 2021-09-16Natural language processing
Automatic processing of labguage
2018-01-11
– 2021-09-16Recurrent neural networks
2016-06-16
– 2021-09-06Convolutional stochastic processes
Moving averages of noise
2021-03-01
– 2021-08-16Grammar induction
2011-05-30
– 2021-08-09Generalised linear models
2016-03-24
– 2021-08-05Neural network activation functions
2017-01-12
– 2021-08-02Learning summary statistics
2020-04-22
– 2021-07-15Multi-task ML
2021-07-14ML on small devices
Putting intelligence on chips small enough to be in disconcerting places
2016-10-14
– 2021-07-13Moral philosophy
2014-08-04
– 2021-07-01Distributed sensing, swarm sensing, adaptive social learning
2014-10-13
– 2021-06-28ML Koans
Passing through the NAND-gate
2021-06-23Voice fakes
2018-09-06
– 2021-06-17Neural net kernels
2019-09-16
– 2021-05-24Infinite width limits of neural networks
2020-12-09
– 2021-05-11Compressing neural nets
pruning, compacting and otherwise fitting a good estimate into fewer parameters
2016-10-14
– 2021-05-07ML benchmarks and their pitfalls
On marginal efficiency gain in paperclip manufacture
2020-08-16
– 2021-04-13Statistics, computational complexity thereof
2020-11-03
– 2021-03-10Mind reading by computer
The ultimate inverse problem
2017-07-01
– 2021-03-03Memory in machine learning
2021-03-03
– 2021-03-03Convolutional Gaussian processes
2021-03-01Stochastic processes on manifolds
2021-03-01Auditory features
descriptors, maps, representations for audio
2019-11-13
– 2021-01-14Statistical mechanics of statistics
2016-12-01
– 2021-01-06Why does deep learning work?
Are we in the pocket of Big VRAM?
2017-05-30
– 2020-12-14Efficient factoring of GP likelihoods
2020-10-16
– 2020-10-26Audiovisuals
Synesthetic and other cross-media audio stunts
2020-10-26Big data ML best practice
2020-09-16
– 2020-09-21Dimensionality 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
– 2020-09-11Neural nets
Designing the fanciest usable differentiable loss surface
2016-10-14
– 2020-09-09Causal graphical model reading group 2020
An introduction to conditional independence DAGs and their use for causal inference.
2020-08-30
– 2020-09-03Causal Bayesian networks
Staged tree models, probability trees …Causalan Bayesian networks
2020-11-01
– 2020-09-01Emulators and surrogate models
Shortcuts in scientific simulation using ML
2020-08-12
– 2020-08-26Bushfire models
2020-09-07
– 2020-08-19Learning of manifolds
Also topological data analysis; other hip names to follow
2014-08-19
– 2020-06-23Deep fakery
2020-06-15Directed graphical models
2017-09-20
– 2020-05-13AV controller interfaces
2019-12-10
– 2020-05-11Likelihood free inference
2020-04-22Analysis/resynthesis of audio
2016-01-15
– 2020-04-09Teaching computers to write music
2016-06-06
– 2020-03-25Learnable indexes and hashes
2018-01-12
– 2020-02-18Learning in adaptive systems
On staring into scopophilic abysses
2019-10-19
– 2020-01-22Controllerism
Making thing happen by waving your arms about on stage
2014-11-17
– 2019-12-10Audio source separation
2019-11-04
– 2019-11-26Tunings
2015-10-29
– 2019-11-18Machine listening
Statistical models for audio
2014-10-10
– 2019-11-12ISMIR 2019
Music Nerds in Delft
2019-11-04
– 2019-11-09Undirected graphical models
2017-09-20
– 2019-10-28Bio computing
2016-05-29
– 2019-10-14Machine vision
2015-01-03
– 2018-11-14Gesture recognition
2014-10-17
– 2018-11-12Quantum-probabilistic graphical models
2017-08-07Marketing psychology
2017-04-27
– 2017-05-29Entity embeddings
2017-04-01Musical metrics and manifolds
2014-09-26
– 2017-03-27Genetic algorithms
2011-04-06
– 2016-12-28Greatest hits
2016-11-19
– 2016-12-12UNSW Stats reading group 2016 - Causal DAGs
An introduction to conditional independence DAGs and their use for causal data.
2016-10-17
– 2016-10-21Inference from disorder
2016-10-19Indirect inference
2014-12-23
– 2015-12-15Pattern machine
2011-06-27
– 2015-11-24