My research is centered around Machine Learning, with broad interests in the areas of Artificial Intelligence, Data Science, Optimization, Reinforcement Learning, High Dimensional Statistics, and ...
A small, dependency-light implementation of two classifier families, built from first principles. LinearClassifierNetwork composes state (input) nodes and association (weighted, thresholded) ...
ml_algorithms_from_scratch.ipynb — linear regression, logistic regression, PCA, a one-hidden-layer neural network with backpropagation, and a dual-form SVM solved by SMO. Written with plain NumPy: no ...
Want only the AI that hits your stack? Build an agent that tracks your companies and topics, and skips everything else. A layer-local training rule that lands within two points of backprop at 1,000 ...
Backpropagation is a global algorithm: a forward pass, then a backward pass, then a weight update, each locked behind the previous one. Brains have no known mechanism for that kind of network-wide ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results