CRNN/LPRNet/STNet + CTC + CCPD
-
Updated
Sep 21, 2024 - Python
CRNN/LPRNet/STNet + CTC + CCPD
Exercises on Machine Learning
INFO7375: Neural Networks & AI
Mambular is a Python package that brings the power of Mamba architectures to tabular data, offering a suite of deep learning models for regression, classification, and distributional regression tasks. This includes models like Mambular, FT-Transformer, TabTransformer and tabular ResNets.
This repository tracks my learning journey in deep learning. It includes various projects and insights, showcasing my progress and enthusiasm for this field.
Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.
Master's thesis project, combining topic clustering, sentiment analysis, optimisation and stock trading RNN's
Repository for PEX0023 Neural Network subject/course on Computer Engineering - UFERSA 🧠
MIT-BIH ECG classification using 1D CNN with TensorFlow3
The Sign Language Interpreter leverages Mediapipe and a hybrid Convolutional Neural Network (CNN) to translate sign language gestures into text. This project is designed to help people who communicate using sign language interact more seamlessly with those who do not understand it.
IMPSy - the Interactive Musical Prediction SYstem
Official repository of the xLSTM.
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
Implementation of a modular, high-performance, and simplistic mamba for high-speed applications
A Telegram bot that takes in an exported WhatsApp chat and uses it to send you text in your and your friend's writing style 😎
An LSTM price prediction model for a Brent crude algorithmic trading bot.
Web app where users can analyze the sentiment of recent tweets using an RNN to determine how society feels about certain issues
LSTM-MISA is an advanced stock analysis tool leveraging the power of Long Short-Term Memory (LSTM) neural networks to predict stock prices and market trends. By incorporating multiple financial indicators, this project offers a comprehensive analysis platform for traders and investors.
This repository provides a basic implementation of self-attention. The code demonstrates how attention mechanisms work in predicting the next word in a sequence. It's a basic implementation that demonstrates the core concept of attention but lacks the complexity of more advanced models like Transformers.
Add a description, image, and links to the rnn topic page so that developers can more easily learn about it.
To associate your repository with the rnn topic, visit your repo's landing page and select "manage topics."