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.

Entrenamiento de algoritmos de ML/DL para la detección y mitigación de ataques DDoS. Enmarcado en mi Proyecto de Título para optar al título de Ingeniero de Ejecución Informático.

Deep convolutional and LSTM feature extraction approach with 784 features.

This project develops a Persian RAG chatbot using LSTM with attention, embedding, tokenization, Google API integration, and Redis for recall. Optimizers like Adam and RMSprop, along with regularization (L1, L2) and data augmentation, enhance the model. Performance is evaluated through BLEU, ROUGE, and METEOR metrics.

Data Visualization and Text Mining course - UNICATT

SC4001 DNN Group Project [NLarge]

Stock Price Prediction using Attention based LSTM

Automated image captioning using CNN and RNN with Flickr8k dataset, leveraging ResNet50 for feature extraction and LSTM for generating natural language descriptions.

Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transformer, LSTM, BiLSTM and so on), multi-GPUs supported, cross-platforms (Windows, Linux, x86, x64, ARM), multimodal model for text and images and so on.

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).

Parallel Reverse Mode Automatic Differentiation in C# for Custom Neural Network Development

"Stock Ticker Predictor" project basically aims to provide a visual representation and analysis of data related to time-series data which is constantly changing. This provides a dashboard to user, made using reactJs - tailwindCSS, displaying current trends and stocks data which uses "LSTM" + "XGBoost" model.

This project explores various music generation models, including autoregressive, CNN, GAN, GRU, LSTM, RNN, Seq2Seq, Transformer, and VAE-based approaches

This project develops a predictive model to identify early signs of mental health issues in adolescents using social media activity, school performance, health records, and an AI chatbot. It analyzes emotional tone, academic changes, and health data, offering personalized recommendations and resources for mental wellness.

VAITP - Vulnerability Attack and Injection Tool for Python

Sentiment Analysis

The code and dataset used in the published paper: Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM

Music Generation using LSTM

RNN-LSTM: From Applications to Modeling Techniques and Beyond - Systematic Review