You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Implementing a neural network from scratch in Python. Building a feedforward neural network and implementing backpropagation for training. Building a working neural network that can be trained on a simple dataset for multi-class classification.
This is our graduation project which aims to control a drone using EEG signals to classify left-right hand and rest state. We have used g.tec Nautilus EEG Headset with 8 electrodes and used g.Recorder software.
This project's aim is to categorize ecommerce products from their images. MobileNetV2 model fine-tuned with 18K retail product images accross 9 categories. Project deployed with Flask and containerized via docker
Successfully developed a fine-tuned DistilBERT transformer model which can accurately predict the overall sentiment of a piece of financial news up to an accuracy of nearly 81.5%.
Successfully developed a fine-tuned BERT transformer model which can accurately classify symptoms to their corresponding diseases upto an accuracy of 89%.
In this notebook, I built gradient boosting classifier and LSTM model to classify and predict the mineral scaling potential of formation water in US shale basins.