CLIP, T-SNE, and UMAP - Master Image Embeddings and Vector Analysis
Master image embeddings and vector analysis techniques like CLIP, T-SNE, and UMAP. Learn to cluster MNIST images, detect duplicates, and explore essential concepts in computer vision and data science through hands-on practice.
Coding a Neural Network from Scratch in Pure JAX - Machine Learning with JAX - Tutorial 3
Learn to build and train a neural network classifier using JAX, including weight visualization, embedding analysis with t-SNE, and dead neuron detection.
Dimensional Reduction Using PaCMAP: From High-Dimensional Data to Vector Spaces - MNIST Case Study
Explore dimensional reduction using PaCMAP algorithm, from basic implementation to advanced applications with MNIST datasets, featuring hands-on Python coding in Colab notebooks.
Unsupervised Feature Learning with Matrix Decomposition - Aedin Culhane, PhD | ODSC East 2018
Explore unsupervised learning techniques for high-dimensional data analysis, focusing on matrix factorization methods and their applications in oncology and precision medicine.
Dimension Reduction - An Overview
Comprehensive overview of dimension reduction techniques, from linear methods like PCA to nonlinear approaches such as LLE, Isomap, t-SNE, and UMAP, with practical application to chemical reaction data.
Application of Unsupervised Learning to AC Susceptibility Measurements of High-Temperature Superconductors
Explore unsupervised learning applications in analyzing AC susceptibility measurements of high-temperature superconductors, focusing on clustering techniques and data representation methods.