Deep convolutional and LSTM feature extraction approach with 784 features.

Cryptocurrency prediction using LSTM (Long Short Term Memory)

Project aims to forecast potato prices in India using LSTM, KNN, and Random Forest Regression, integrating historical data on prices, regional stats, and rainfall patterns. Targeting agricultural stakeholders for informed decision-making.

基于LSTM针对长时序的气温、降水、气压、相对湿度、风速等气象站点数据，对尼洋河径流进行模拟预测

BSP 2 - Housing Market Dynamics: Exploratory Analysis and Future Behavior Forecasting

Utilizing LSTM Neural Networks to forecast energy cosumption trends with time series analysis. Employing Collaborative Filtering with Matrix Factorization and SVD, the system suggests personalized actions based on user behavior, fostering energy conservation.Leveraging Isolation Forest to detect anomalies in consumption patterns.

This repository contains a collection of time series forecasting models, including: Statistical Models Simple and robust models that leverage statistical techniques to forecast future values.

This repository contains all my Deep Learning code using Python language

scripts used for neural decoding of single and multi unit auditory cortex data

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.

testing MLP, DQN, PPO, SAC, policy-gradient by snake

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.

The practitioner's forecasting library

Creating a PyTorch LSTM and Transformer to classify movies by genre and visualizing the LSTM's reasoning process

The "New Word Predictor" is a smart writing tool that helps you type faster and better. As you type, it suggests words and phrases to complete your sentences. It learns from how you write and adapts to your style over time, making it easier for you to express yourself and discover new words effortlessly.

Paint2code - a lightweight tool designed to transform your hand-drawn sketches into functional HTML code.

This project involves developing a machine learning model to predict user preferences in chatbot conversations, using a dataset of head-to-head responses from various large language models. The goal is to enhance chatbot-human interactions by aligning chatbot responses more closely with human preferences.

This repository contains the code and scripts used in my thesis project, which aims to build various BERT and LSTM models to detect AI generated texts in both English and Arabic languages.

RNN(SimpleRNN, LSTM, GRU) Tensorflow2.0 & Keras Notebooks (Workshop materials)

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.