Part-of-Speech Tagging using Bidirectional Long-Short Term Memory

Deep Learning class projects from Kagle. All projects are individual projects conducted by me using pyhton (keras, tensor-flow, matplotlib and other libraries). Different Deep Neural Network (DNN) methods were used and results were compared based one efficiency and accuracy. Results and conclusions based on results were reported.

Simulation of "Triggering Proactive Business Process Adaptations via Online Reinforcement Learning" paper with proper steps and recreating the results

Assignments of my CST Part III Natural Language Processing (L90) module

Documentation related to RNN

Classifying the sentiment of IMDb reviews by implementing long short-term memory networks

Time Series Forecasting with Neural Networks

Recurrent Neural Networks (RNN's) for sentiment analysis on IMDB dataset from keras....

RNN, Word Embedding, LSTM, Classification

Major Neural Network Architectures - recurrent neural networks, convolutional neural networks, long-short-term-memory, autoencoders, recommender systems, artificial general intelligence

Our study utilizes BERT and LSTM models alongside Monte Carlo Dropout (MCD) on the Yelp Labelled Dataset. MCD bolsters robustness by introducing uncertainty through neuron dropout. The BERT-embedded MCD achieves an impressive 91.75% accuracy, surpassing the LSTM model.

Toy example of RNN LSTM in TensorFlow

Certificates of the Deep Learning Specialization from Coursera (2020)

This repo contains all the necessary files to give you an idea of the complexity of an undergrad capstone project.

modelo de inteligencia artificial Long Short-term Memory (LSTM) para predecir ventas diarias

Hand gesture control of a robot. Research conducted at Hochschule Fulda, Germany for fulfillment of undergraduate thesis.

Train a Long short term memory network to translate German text to English

Deep Learning Bidirectional Long Short Term Memory model to classify toxic comments into various parameters of toxicity

This binary classification model uses Machine Learning to determine if tweets are positive or negative. The model involves text-handling techniques such as stemming, filtering, stop word removal, and text vectorization.