🎨 Generate unique prompts to create stunning beauty images effortlessly with genbeauty, your go-to tool for AI-driven image generation.

🖼️ Run Segformer efficiently for rapid image and video segmentation with minimal setup. Streamline your workflow and enhance your projects quickly.

🧠 Implement convolutional and recurrent neural networks in TensorFlow Keras to handle image and text datasets, enhancing model performance through advanced techniques.

🌐 Showcase your skills and achievements with this modern, responsive personal portfolio website built using HTML, CSS, and JavaScript.

🔍 Enhance anomaly detection with AD-DINOv3, a framework adapting DINOv3 for zero-shot scenarios through advanced calibration techniques.

Country Explorer is a web application that lets you explore countries worldwide using free public APIs. Discover each nation's name, flag, and detailed information with simple filtering options. 🗺️🌍

This repo contains the static Jekyll website source for MlPlatform.org

How to create a small LLM built with the transformer architecture in Python.

Analyzing X-ray reflectometry data using the Parratt recursion formalism with Nevot-Croce roughness corrections.

Blogosphere

Application of the R package cpfa to real datasets.

The Multi-Cancer Classification Tool is a deep learning-powered web application designed to classify different classes of cancers based on medical images, providing accurate and fast results to aid medical specialists in diagnosis.

Stock Price Prediction Using LSTM is an AI-powered tool built with Python, TensorFlow, and Streamlit. It lets users train LSTM models on real-time stock data and visualize predictions interactively.

Neural is a domain-specific language (DSL) designed for defining, training, debugging, and deploying neural networks. With declarative syntax, cross-framework support, and built-in execution tracing (NeuralDbg), it simplifies deep learning development.

NYCU CSIC30014 Lab2: EEG Classification with EEGNet (87%+ accuracy, optimized hyperparameters, BCI Competition III dataset)

Official site of Biophys group at Unito

INFO 527 — Neural Networks: Assignment 4. Implementation of deep learning architectures using TensorFlow Keras, including convolutional neural networks (CNNs) for image and text classification and recurrent neural networks (RNNs) for sequence modeling. Part of the Master’s in MIS/ML program at the University of Arizona.

Deep learning approach for multiclass classification of mice based on cortical protein expression and experimental conditions in Python.

Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

Optimized CNN achieving ~90% accuracy with 38.6% parameter reduction for production-ready digit recognition