Categories Meta Moved to Princeton! Introspection in AI Learning Theory: Purely Theoretical? Is AI scary? It Depends on the Model Markov chain centenary Should neurons be interpretable? New Blog Neuroscience What is the Computational Capacity of the Brain? Introductory post, and the invariance problem Priors for Functional and Effective Connectivity Should neurons be interpretable? The "Computation" in Computational Neuroscience Healthy Competition? Machine Learning Discrete Object Generation with Reversible Inductive Construction Efficient Optimization of Loops and Limits with Randomized Telescoping Sums Which research results will generalize? Prior knowledge and overfitting ICML Highlight: Fast Dropout Training Testing MCMC code, part 1: unit tests Introspection in AI Machine Learning Glossary Optimal Spatial Prediction with Kriging Upcoming Conferences Variational Inference (part 1) Geometric means of distributions Learning Theory: What Next? Data compression and unsupervised learning, Part 2 An Auxiliary Variable Trick for MCMC What is representation learning? High-Dimensional Probability Estimation with Deep Density Models Data compression and unsupervised learning Learning Theory: Purely Theoretical? Getting above the fray with lifted inference What the hell is representation? * Predictive learning vs. representation learning Dealing with Reliability when Crowdsourcing The Natural Gradient Complexity of Inference in Bayesian Networks Markov chain centenary DPMs and Consistency Unbiased estimators of partition functions are basically lower bounds Priors for Functional and Effective Connectivity A Continuous Approach to Discrete MCMC Bayesian nonparametrics in the real world Hashing, streaming and sketching On representation and sparsity Nonparanormal Activity Discriminative (supervised) Learning Method of moments Turning Theory into Algorithms The "Computation" in Computational Neuroscience Learning Image Features from Video Statistics The Central Limit Theorem Optimal Spatial Prediction with Kriging Fisher information Pseudo-marginal MCMC Variational Inference (part 1) The Alias Method: Efficient Sampling with Many Discrete Outcomes High-Dimensional Probability Estimation with Deep Density Models A Parallel Gamma Sampling Implementation Exponential Families and Maximum Entropy Correlation and Mutual Information Variograms, Covariance functions and Stationarity Dealing with Reliability when Crowdsourcing The Natural Gradient It Depends on the Model DPMs and Consistency Unbiased estimators of partition functions are basically lower bounds A Continuous Approach to Discrete MCMC Bayesian nonparametrics in the real world Asymptotic Equipartition of Markov Chains The Poisson Estimator Computation Testing MCMC code, part 2: integration tests Testing MCMC code, part 1: unit tests JIT compilation in MATLAB The Gumbel-Max Trick for Discrete Distributions Pseudo-marginal MCMC The Alias Method: Efficient Sampling with Many Discrete Outcomes A Parallel Gamma Sampling Implementation Getting above the fray with lifted inference What is the Computational Capacity of the Brain? The Natural Gradient Aversion of Inversion Computing Log-Sum-Exp Probability The ELBO without Jensen, Kullback, or Leibler The Central Limit Theorem The Gumbel-Max Trick for Discrete Distributions Pseudo-marginal MCMC Chernoff's bound Variational Inference (part 1) An Auxiliary Variable Trick for MCMC A Geometric Intuition for Markov's Inequality High-Dimensional Probability Estimation with Deep Density Models Exponential Families and Maximum Entropy The Fundamental Matrix of a Finite Markov Chain Disconnectivity graphs Compression Compressing genomes Data compression and unsupervised learning, Part 2 Data compression and unsupervised learning Ramblings Data compression and unsupervised learning, Part 2 Data compression and unsupervised learning Recent work Discrete Object Generation with Reversible Inductive Construction Efficient Optimization of Loops and Limits with Randomized Telescoping Sums A Bayesian Nonparametric View on Count-Min Sketch An Auxiliary Variable Trick for MCMC High-Dimensional Probability Estimation with Deep Density Models Blog Vitruvion: A Generative Model of Parametric CAD Sketches Using 3D Printing to Develop Rapid-Response PPE Manufacturing The ELBO without Jensen, Kullback, or Leibler Discrete Object Generation with Reversible Inductive Construction Lab Progress: Laser Cutter Efficient Optimization of Loops and Limits with Randomized Telescoping Sums Lab Progress: 3D Printer Enclosures Lab Complete: Assembling Tormach A Bayesian Nonparametric View on Count-Min Sketch New Lab: Demolition Moved to Princeton! Which research results will generalize? Prior knowledge and overfitting ICML Highlight: Fast Dropout Training Testing MCMC code, part 2: integration tests Compressing genomes Testing MCMC code, part 1: unit tests The Central Limit Theorem JIT compilation in MATLAB Introspection in AI Machine Learning Glossary Optimal Spatial Prediction with Kriging Fisher information Video Video: Introduction to Convex Optimization Video: Basics of Optimization Video: Information Theory Basics Video: The Gaussian Distribution Video: Useful Inequalities and Limit Theorems Video: Dependence and Independence Video: Basics of Joint Probability Video: Some Useful Probability Distributions Video: Probability Density and Mass Functions Video: Probability Spaces and Random Variables Video: Why is Probability Important to Machine Learning? Video: Why is the Gradient the Direction of Steepest Ascent Video: Derivative as the Best Affine Approximation Video: Partial Derivatives Video: Basics of Differentiation Starting a YouTube Channel