Jethro's Braindump

  • A critique of pure learning and what artificial neural networks can learn from animal brains
  • A Distributional Code for Value in Dopamine-based Reinforcement Learning
  • Actor-Critic
  • Alexander Rush
  • All-reduce
  • alonso_current_2019: Current Research Trends in Robot Grasping and Bin Picking
  • And the Bit Goes Down: Revisiting the Quantization of Neural Networks
  • Anti-fragile Ideas
  • Applying Forecasting in Finance
  • Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
  • Are We Smart Enough to Know How Smart Animals Are?
  • Arguments Against Bayesian Inference
  • ARM Assembly Programming
  • Art
  • Article: An Opinionated Guide to ML Research
  • Artificial Intelligence
  • Asian Cinema
  • Ask HN: How do I learn C properly? | Hacker News
  • Attention (ML)
  • Attention Allocation in Open Source
  • Autoencoder
  • Awk
  • Bad Is Stronger Than Good
  • BART
  • Bayes Filter
  • Bayesian Deep Learning
  • Bayesian Inference
  • Bayesian Statistics
  • Benjamin Graham
  • Bin Picking
  • BitTorrent
  • Blockchain
  • Bloom Filter
  • Books
  • Branch Prediction
  • Brier Scores
  • Building a PC
  • Business
  • Byron Boots - Perspectives on Machine Learning and Robotics
  • C++ Language
  • Canonical Correlation Analysis
  • Capitalism
  • Causality, part 1 - Bernhard Schölkopf - MLSS 2020, Tübingen - YouTube
  • Cedric Chin
  • Celeste Kidd
  • Change of Variables Theorem
  • chen20_simpl_framew_contr_learn_visual_repres: A simple framework for contrastive learning of visual representations
  • chen_big_2020: Big Self-Supervised Models are Strong Semi-Supervised Learners
  • China Economics
  • CMake
  • Co-learning
  • Code Litmus Tests
  • Coding Interview Cheatsheet
  • Coding Interview Preparation
  • Cognitive Hierarchy Model
  • Cognitive Task Analysis
  • Collaborative Editing
  • Common Statistical Tests Are Linear Models
  • Compilers
  • Computer Networking
  • Computer Organization
  • Computer Vision
  • Concept Grounding
  • Conditional Random Fields
  • Config Management
  • Conor White-Sullivan
  • Consciousness
  • Contrastive Methods
  • Control As Inference
  • Conversation
  • Convolutional Neural Networks
  • Copy Editing
  • Copying Better: How To Acquire The Tacit Knowledge of Experts
  • Courtland Allen
  • Credit Assignment in Spiking Neural Networks
  • Critical Thinking
  • Cross-modal Hashing
  • Cryptography
  • CSS
  • Cuckoo Filters
  • Daniel Kahneman
  • Data Science
  • Data Structures and Algorithms
  • Data Visualization
  • Databases
  • Datacouncil.ai Conference Notes
  • DBSCAN
  • Deep Boltzmann Machines
  • Deep Learning
  • Deep Learning Tools
  • Deep Learning With Bayesian Principles - Emtiyaz Khan
  • Deep Reinforcement Learning
  • Deep Reinforcement Learning That Matters
  • Definition of Deep Learning
  • Designing Data-Intensive Applications
  • Designing Good Forecasts
  • Dev Ops
  • Differentiable plasticity: training plastic neural networks with backpropagation
  • Distributed Reinforcement Learning
  • Docker 101
  • Documentation
  • Documentation Generators
  • Double-entry Accounting
  • DVS Cameras
  • Dynamic Time Warping
  • EKF Localization
  • Elisp: Buffer-passing Style
  • Emacs
  • Emacs Lisp
  • Emacs Should Be Emacs Lisp - Tom Tromey
  • Empirical Risk Minimization
  • Emtiyaz Khan
  • Energy-based Models
  • Entropy
  • Event Representations
  • Event-based Vision
  • Everything Compounds
  • Evolving Connectionist Systems
  • Evolving Spiking Neural Networks
  • Exchangeability
  • Expectation Maximization and Mixture Models
  • Experience Replay
  • Experimental Data Science
  • Exploration In Reinforcement Learning
  • Exponential Family
  • Extended Kalman Filter
  • Fast Neural Network Training
  • Feedback Alignment and Random Error Backpropagation
  • Feynman Technique
  • Finance
  • Financial Derivative
  • Find (CLI Tool)
  • Fisher information
  • Fitness
  • Forward Contracts
  • Free-Energy Reinforcement Learning
  • Futures Contract
  • Game API Design
  • Game Design
  • Gaussian Filter
  • Gaussian Processes
  • GCC
  • GDC Vault - Exploring the Tech and Design of 'Noita'
  • Generalization In Reinforcement Learning
  • Generalized Value Functions
  • Generative Models
  • Getting Things Done (GTD)
  • Gibbs Sampling
  • Gibbs' Inequality
  • Git
  • Git Scalar
  • Google - Site Reliability Engineering
  • Google Cartographer
  • Google Cloud Platform
  • Google DNS
  • Gpipe
  • Grasp Estimation
  • Grid & Monte Carlo Localization
  • GuildAI
  • Hacking
  • Hadoop
  • Haskell
  • Hidden Markov Model
  • Hierarchical Models
  • High Performance Natural Language Processing
  • Hindsight Experience Replay
  • Histogram Filter
  • hjelm_learning_2019: Learning deep representations by mutual information estimation and maximization
  • Hopfield Network
  • How To Be a Good Forecaster
  • How to brainstorm great business ideas
  • How To Know - Celeste Kidd
  • How to Make Yourself Into a Learning Machine - Superorganizers
  • How To Read A Book
  • How To Take Smart Notes
  • How To Write a Technical Paper
  • HTTP
  • Human Behaviour As Optimal Control
  • I-Diagrams
  • If You're Not Writing a Programming Language, Don't Use A Programming Language - Leslie Lamport
  • Ignore What Everyone Else is Doing
  • Imagineering in a Box | Storytelling | Arts and humanities | Khan Academy
  • Imitation Learning
  • Importance Sampling
  • Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data
  • Information Bottleneck in Deep Neural Networks
  • Information Filter
  • Information Theory
  • Information-Theoretic Reinforcement Learning
  • Interactive Closest Point
  • Interval Estimation in Bayesian Statistics
  • Introduction to D3 / MIT Visualization Group / Observable
  • Inverse Reinforcement Learning
  • Investing In ETFs
  • Investment
  • IS1103: Computing and Society
  • Ising Models
  • Iterative Closed Point
  • Java
  • JavaScript
  • Jeffreys Prior
  • Jensen's Inequality
  • jing_self-supervised_2019: Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
  • John Schulman
  • John Wiegley
  • K-means
  • Kalman Filter
  • Kl Divergence
  • Knowledge Distillation
  • lagorce_hots_2017: HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition
  • Laplace's Method
  • Large Batch Training
  • LARS Optimizer
  • Latent Dirichlet Allocation
  • LaTeX
  • Leaky Integrate-And-Fire
  • Learning
  • Learning How To Do Hard Things
  • Learning How To Learn
  • LeCun's Cake Analogy
  • Leslie Lamport
  • Likelihood Field Model
  • Likelihood Principle
  • Linear Algebra
  • Linux
  • Local Registration
  • Lottery Ticket Hypothesis
  • Lsof
  • LU Decomposition
  • Machine Learning
  • Machine Learning Algorithms
  • Machine Teaching
  • mahler_dex-net_2017: Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
  • Making Sense of Vision and Touch: Multimodal Representations for Contact-Rich Tasks | SAIL Blog
  • Making Transformer Models Efficient
  • Map Matching
  • Markov Chains
  • Markov Decision Process
  • Markov Localization
  • Markov Logic Networks
  • Markovian Assumption
  • Martin Kleppmann
  • Matplotlib
  • Mental Models
  • Meta Learning
  • Metropolis-Hastings Method
  • Michael Nielsen
  • Mixed Precision Training
  • Model Compression
  • Model-Based Reinforcement Learning
  • Monte Carlo Methods
  • Monte Carlo Tree Search
  • Motion Model With Maps
  • Multi-modal Alignment
  • Multi-modal Autoencoders
  • Multi-modal Fusion
  • Multi-modal Machine Learning
  • Multi-modal Representation
  • Multi-modal Translation
  • Multi-variable Calculus
  • Multiple Learning Kernel
  • nasarGrandPursuitStory2011: Grand pursuit: The story of economic genius
  • Nat Eliason
  • Natural Language Processing
  • Negotiation
  • Neural Network Optimizer
  • Neural Ordinary Differential Equations
  • NeurIPS
  • Neuroscience and Reinforcement Learning
  • Neuroscience Experimental Evidence
  • Neuroscience ⭐
  • Nix/NixOS
  • Nolla Games
  • Non-informative Priors
  • Non-parametric Filters
  • Normalizing Flows
  • Note-taking
  • Numpy
  • OCaml
  • Occam's Razor
  • Occupancy Grid Mapping
  • Odometry Motion Model
  • Operating Systems
  • Optimal Control and Planning
  • Optimization
  • Optionality
  • Options (Finance)
  • Options Framework
  • Org-Mode
  • Outside/Inside View
  • PAC Learning
  • Papers
  • PARA Method
  • Parameter Servers
  • Partially Observable Markov Decision Processes (POMDPs)
  • Particle Filter
  • PDF Cropping
  • PDF Nup
  • Pdf Tools
  • Petri Purho
  • Playing Atari with Deep RL
  • Podcasts
  • Point Estimation in Bayesian Statistics
  • Policy Gradients
  • Portfolio Composition
  • Post YC Depression
  • Prediction is the Essence of Intelligence
  • Presentations
  • Principles of Effective Research | Michael Nielsen
  • Privacy
  • Probabilistic Graph Models
  • Probability Theory
  • Productivity
  • Programming Languages
  • Programming Methodology
  • Progressive Summarization
  • Pruning Neural Networks
  • Pulumi
  • Python
  • Python Default Parameter Values
  • Python Import Resolution
  • Python Packaging
  • Q-Learning
  • Quantitative Reasoning
  • Quantization
  • Rademacher Complexity
  • Random Variables
  • Random Walks in Finance
  • Range Finder Model
  • RANSAC
  • React
  • Reading
  • Real Estate Investment Trusts
  • Recognition-primed Decision-making Model
  • Recommender Systems
  • Red-Black Tree
  • Reference Prior
  • Regression
  • Regression to the Mean
  • Reichenbach's principle
  • Reinforcement Learning
  • Rejection Sampling
  • Research
  • Residual Neural Networks
  • Restricted Boltzmann Machines
  • Richard Feynman
  • Richard Hamming
  • Riken AIP Workshop 2019
  • Roam Research
  • Robot Grasping
  • Robot Kinematics
  • Robot Localization
  • Robot Motion
  • Robot Operating System (ROS)
  • Robotics
  • Robotics Algorithms
  • Robotics Probabilistic Generative Laws
  • Rover
  • RSS 2020 Workshops: Visuotactile Sensors for Robust Manipulation - From Perception to Control
  • RSS 2020, Early Career Award Keynote + Q&A: Jeannette Bohg - YouTube
  • RSS 2020, Early Career Award Keynote + Q&A: Luca Carlone - YouTube
  • RSS Feeds
  • Running
  • Rust
  • Sam Greydanus
  • Scala
  • Security
  • Self-attention
  • Self-supervised Learning
  • Self-Supervised Representation Learning
  • Sentences should branch to the right
  • Setting Up a Raspberry Pi
  • Setting up a Static IP Address on Raspberry Pi
  • Setting up Dynamic DNS on Raspberry Pi
  • Setting up Emacs on Mac
  • Shell
  • Simultaneous Localization and Mapping
  • Singapore Dollar Nominal Effective Exchange Rate
  • Singapore Society
  • Single Layer XOR
  • Site Reliability
  • Sleep
  • Slice Sampling
  • Smoothed Spiking Neural Networks
  • SNN Software
  • Software Engineering
  • Sonke Ahrens
  • Spaced Repetition
  • Spark
  • Speeding Up the Training of Deep Neural Networks
  • Spike Train Metrics
  • Spike Train Mutual Information
  • Spiking Datasets
  • Spiking Neural Networks
  • Spiking Neurons (Literature Review)
  • SSNLP Conference Notes
  • State Estimation
  • Statistical Distributions
  • Statistical Learning
  • Statistical Mechanics in Financial Markets
  • Statistical Mechanics in Financial Markets
  • Statistical Methods for Finance
  • Statistical Testing
  • Statistics
  • Stochastic Processes
  • Storytelling
  • Structural Causal Model
  • Studying
  • Sufficient Statistics
  • Support Vector Machines
  • Surrogate Gradient Learning In Spiking Neural Networks
  • Svelte
  • Swift
  • Synaptic Current Model
  • System Design
  • Systems Programming
  • t-distribution
  • Talks: Emacs Lisp Development Tips with John Wiegley
  • Temp Coding with Alpha Synaptic Function
  • Temporal Difference Learning
  • Testing sync at Dropbox - Dropbox
  • The Annotated Transformer
  • The Art Of Doing Science And Engineering
  • The art of storytelling | Pixar in a Box | Partner content | Khan Academy
  • The Art Of Unix Programming
  • The Average Expert is as Accurate as A Dart-throwing Chimpanzee
  • The Bias-Complexity Tradeoff
  • The C Language
  • The Collectors' Fallacy
  • The Collector’s Fallacy • Zettelkasten Method
  • The Fermi Estimate
  • The Good Judgment Project
  • The Hidden Life of Trees: What They Feel, How They Communicate
  • The Intelligent Investor
  • The Law of Diminishing Returns
  • The most successful malleable system in history | Malleable Systems Collective
  • The opt-out illusion - Technology - TLS
  • The Paths Perspective on Value Learning
  • The Svelte Compiler Handbook | Tan Li Hau
  • The Technique of Inversion
  • Theory Of Computation
  • Three-pass Technique
  • Time Surface
  • Tom Tromey
  • Topic Modeling
  • Transfer Learning
  • Transformer
  • Travel
  • Trigger List
  • Two Levels Of Inference
  • Uncertainty in Robotics
  • Unix
  • Unsupervised Learning
  • Variational Autoencoders
  • Variational Inference
  • VC-Dimension
  • Velocity Motion Model
  • Version Control
  • VFS for Git
  • VisGel
  • Visual Basic
  • Vocabulary
  • Voxel Grid
  • Web Development
  • Web Framework
  • Web Performance
  • What happens when we type a simple command on shell?
  • What to write down when you’re reading to learn – Aceso Under Glass
  • When Bloom filters don't bloom
  • Why Svelte is our choice for a large web project in 2020
  • Wisdom
  • Wood Wide Web
  • Work Clean
  • Writing
  • Writing Articles
  • Writing Books
  • Writing with Zettekasten
  • wu_stochastic_2020: Stochastic Normalizing Flows
  • XGBoost
  • Yann LeCun
  • You and Your Research - Richard Hamming
  • Zeigarnik Effect
  • Zero shot Learning
  • Zettelkasten
  • zhu_ev-flownet_2018: EV-FlowNet: self-supervised optical flow estimation for event-based cameras
  • zhu_unsupervised_2018: Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion
  • 🌿 What I'm Doing Now