Stock price prediction using LSTM and 1D Convoltional Layer implemented in keras with TF backend on daily closing price of S&P 500 data from Jan 2000 to Aug 2016

Building a HTTP-accessed convolutional neural network model using TensorFlow NN (tf.nn), CIFAR10 dataset, Python and Flask.

Solve complex real-life problems with the simplicity of Keras

Deep learning using CNN in tensorflow on Kaggle image dataset containing 87,900 different healthy and unhealthy crop leaves spanning 38 unique classes.

Verilog Codes for various Design

Ensemble Classifier

A collection of Jupyter notebooks containing various MNIST digit and fashion item classification implementations using fully-connected and convolutional neural networks (CNNs) built with TensorFlow and Keras. 2020.

A CNN Architecture classifies 14 kinds of automobile parts.

Relationship Extraction using a Bi-directional GRU v/s CNN with multiple layers and max-pooling

Deep Convolutional Encoder-Decoder Architecture implemented along with max-pooling indices for pixel-wise semantic segmentation using CamVid dataset.

Deep Convolutional Encoder-Decoder Architecture implemented along with max-pooling indices for pixel-wise semantic segmentation using CamVid dataset.

Visualizing effects of CNN filters and Max Pooling on images.

Machine Learning For Beginners - Rock, Paper, dan Scissors Image Classification

This project utilizes a CNN model to classify cat and dog images through training and testing processes. The model is created using the Keras library on the TensorFlow backend.

Project for lecture 5 Neural Networks to "Artificial Intelligence with Python" Harvard course

AI model from scratch in C++ for image classification (MNIST dataset)

Denoising Diffusion Medical Model (DDMM) on PyTorch for generating datasets of Acute Lymphoblastic Leukemia 🩺💜

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.