Feature engineering is the process of using domain knowledge to extract features from raw data via data mining techniques. These features can be used to improve the performance of machine learning algorithms. Feature engineering can be considered as applied machine learning itself.
Pathology Foundation Model - Nature Medicine
- foundation
- foundation-model
- histopathology
- mahmoodlab
The repository host gives no description.
[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation
Bayesian Deep Learning Benchmarks
- bayesian-deep-learning
- benchmark-framework
- diabetic-retinopathy
VQVAEs, GumbelSoftmaxes and friends
Course materials for: Geospatial Data Science
TIPSv2 (CVPR'26) and TIPS (ICLR'25)
- image-text
- spatial-understanding
- vision-encoder
A scikit-learn compatible library for graph kernels
- graph-kernels
- graph-classification
- scikit-learn
- graph-mining
Code examples for the book titled Introduction to GIS Programming
Fake News Detection in Python
- python
- text-classification
- text-analysis
- fake-news
A scikit-learn-compatible Python implementation of ReBATE, a suite of Relief-based feature selection algorithms for Machine Learning.
Fusing Histology and Genomics via Deep Learning - IEEE TMI
- pathomic
- fusion
- multimodal
- pathology
TranslatedLLM teaching material for high school students: based on Karpathy's microgpt, for Google Colab
Repository for Nicheformer: a foundation model for single-cell and spatial omics
Breaking captchas using torch
The repository host gives no description.
A database of paths that represent the mechanism of action from a drug to a disease in an indication.
Peax is a tool for interactive visual pattern search and exploration in epigenomic data based on unsupervised representation learning with autoencoders
Exercises for the lecture "Selected Topics in Audio Signal Processing"
Machine learning for Analysis of Proteomics in Spatial biology - Nature Communications
- cell-annotation
- multiplexed-imaging
- mpif
Deciphering cell-cell communication from spatially resolved transcriptomic data at single-cell resolution with subgraph-based attentional graph neural network
A coding exercise: let's convert dirty machine learning code into clean code using a Pipeline - which is the Pipe and Filter Design Pattern applied to Machine Learning.