Fast and customizable framework for automatic ML model creation (AutoML)

A multi-platform GUI for bit-based analysis, processing, and visualization

Binary and Categorical Focal loss implementation in Keras.

autosklearn-zeroconf is a fully automated binary classifier. It is based on the AutoML challenge winner auto-sklearn. Give it a dataset with known outcomes (labels) and it returns a list of predicted outcomes for your new data. It even estimates the precision for you! The engine is tuning massively parallel ensemble of machine learning pipelines…

Detecting Autism Spectrum Disorder in Children With Computer Vision - Adapting facial recognition models to detect Autism Spectrum Disorder

1st place solution of RSNA Screening Mammography Breast Cancer Detection competition on Kaggle: https://un5gmtkzghdxcm45v6mj8.julianrbryant.com/competitions/rsna-breast-cancer-detection

Multi-modal AI-generated content detection: image, video, and audio. Benchmarks, training code (DINOv2, DINOv3, ReStraV, BreathNet), and evaluation pipeline for real vs. synthetic classification with calibration-aware metrics.

Implementation of Focal Loss (Lin et al., 2017, Facebook AI Research) for handling class imbalance by focusing learning on hard, misclassified examples.

[ICMLSC 2018] On Breast Cancer Detection: An Application of Machine Learning Algorithms on the Wisconsin Diagnostic Dataset

A set of deep learning models for FRB/RFI binary classification.

2018-腾讯广告算法大赛-相似人群拓展(初赛)：10th/1563 (Top 0.64%)

Custom Loss Functions and Evaluation Metrics for XGBoost and LightGBM

Malicious URL detector using keras recurrent networks and scikit-learn classifiers

🦓 AI-powered OpenStreetMap tool for importing zebra crossings

WNUT-2020 Task 2: Identification of informative COVID-19 English Tweets

Binary Image Classification in TensorFlow

🔇 A production-grade deep learning system for real-time drone/UAV detection through acoustic signature analysis. Converts raw audio to Mel-Spectrograms and classifies using a custom CNN. Features auto-dataset ingestion, defense-optimized metrics (high recall), early stopping, model checkpointing, and a ready-to-use inference API.

LightGBM for handling label-imbalanced data with focal and weighted loss functions in binary and multiclass classification

Glaucoma detection automation project. Trained a binary image classifier using CNNs and deployed as a streamlit web app. It takes eye (retinal scan) image as input and outputs whether the person is affected by glaucoma or not.

Multilayer Perceptron Neural network for binary classification between two type of breast cancer ("benign" and "malignant" )using Wisconsin Breast Cancer Database