Demonstration notebooks for Machine Learning

scGEAToolbox: Matlab toolbox for single-cell gene expression analyses

The unsupervised learning problem trains a diffeomorphic spatio-temporal grid, that registers the output sequence of the PDEs onto a non-uniform parameter/time-varying grid, such that the Kolmogorov n-width of the mapped data on the learned grid is minimized.

DataHigh: A graphical user interface for visualizing and interacting with high-dimensional neural activity

A fast units and dimensions library with support for static dimensionality checking and protobuffer serialization.

Comparison of various Dimensionality Reduction techiniques and Visualization of the same.

A rule-based foundational ontology and applied physics framework exploring definition discipline, spacetime resistance, gravity, cognition, and field-first engineering.

The Golomb Universe

Visualization and embedding of large datasets using various Dimensionality Reduction (DR) techniques such as t-SNE, UMAP, PaCMAP & IVHD. Implementation of custom metrics to assess DR quality with complete explaination and workflow.

Code for the paper, "The Curse of Dimensionality: Inside Out", DOI = 10.13140/RG.2.2.29631.36006.

Just a bunch of tools made in TypeScript.

Minimal PCA library based on numpy and practical examples of dimensionality reduction use of the principal components in ETF market analysis.

montecarlo methods

Analysis code for dimensionality and connectivity across the macaque ventral visual stream (THINGS Ventral Stream Spiking Dataset).

Return the shape of a provided ndarray.

Return the shape of a provided ndarray.

A Python project for generating and testing bipolar, multi-dimensional number sequences, representing scope and essence through layers of dimensions.

The power of the framework I have mapped is true for it has explained the intimate workings of our universe to me. Come on this journey of exploration with me into this wonderful frontier! But be warned, your 1st principles will be rigorously challenged; can you defend them?

Bond Order Scaling Law: 100% accurate molecular vs crystalline prediction for binary compounds. Cascade classifier L4→L5→L6 covering 76K JARVIS-DFT materials. No DFT required.

My talk to UFRJ Ecology Graduate Program