Overparameterization and overfitting are common concerns when designing and training deep neural networks. Network pruning is an effective strategy used to reduce or limit the network complexity, but often suffers from time and computational intensive procedures to identify the most important connections and best performing hyperparameters. We s…

In this repository I have utilised 6 different NLP Models to predict the sentiments of the user as per the twitter reviews on airline. The dataset is Twitter US Airline Sentiment. The best models each from ML and DL have been deployed. It employs text preprocessing,

We build a chatbot by implementing machine learning and natural language processing.

Major Project in Final Year B.Tech (IT). Live Stream Sign Language Detection using Deep Learning.

Using data to help us choice high quality wine

Fraud Classification using Deep Learning Techniques

A supermarket chain called Good Seed wanted to see if Data Science could help them comply with the law by ensuring that they did not sell age-restricted products to underage customers. My task was to build and evaluate a model to verify a person's age.

Content: Structure of CNN, Convolutional layer, Pooling layer, Fully connected layer, Dense layer, output, Image classification, Creating, compiling and training the model on epochs, testing the model on gradio

A beginner's investigation into the world of neural networks, using the MNIST image dataset

NLP-FinHeadlines-MoodTracker is a NLP project utilising sentiment analysis on financial news headlines. It employs a combination of CNN and LSTM layers to predict sentiment (positive, negative, neutral). The model incorporates an embedding layer, 1D convolution, max pooling, bidirectional LSTM, dropout, and dense layer for sentiment classification.

Implementations of different types of AutoEncoders

Implementation and Comparison of Multiclass Synonyms Equivalence Classifiers based on Textual Similarity Metrics using Keras