BabyGPT: Build Your Own GPT Large Language Model from Scratch Pre-Training Generative Transformer Models: Building GPT from Scratch with a Step-by-Step Guide to Generative AI in PyTorch and Python

This library provides a set of functionalities for different type of deep learning (and ML) algorithms in C

PREDICT THE BURNED AREA OF FOREST FIRES WITH NEURAL NETWORKS

Predicting Meta stock prices using MLP, RNN and LSTM models.

Predicting Turbine Energy Yield (TEY) using ambient variables as features.

Python from-scratch implementation of a Neural Network Classifier. Dive into the fundamentals of approximation, non-linearity, regularization, gradients, and backpropagation.

Concrete cracking is a major issue in Bridge Engineering. Detection of cracks facilitates the design, construction and maintenance of bridges effectively.

Concrete cracking is a major issue in Bridge Engineering. Detection of cracks facilitates the design, construction and maintenance of bridges effectively.

ANN model to predict customer churn based on some information about the customer and used Dropout regulization to avoid overfitting in my model.

A collection of deep learning exercises collected while completing an Intro to Deep Learning course. We use TensorFlow and Keras to build and train neural networks for structured data.

Fall 2021 Introduction to Deep Learning - Homework 1 Part 2 (Frame Level Classification of Speech)

In this project, we explored two approaches for detecting fake images (fake vs. real) using Bayesian Convolutional Neural Networks (BCNNs), with a particular focus on estimating the model's uncertainty. The ability of a model to quantify its confidence in a prediction is crucial, especially in sensitive tasks like detecting deepfakes or manipulated

Annotated vanilla implementation in PyTorch of the Transformer model introduced in 'Attention Is All You Need'.

Translates the live video feed from opencv into text format and displays this onto the frame. Uses LSTM, Dropouts, Regularizers and Learning Rate Scheduler

Summary of Assignment One from the Second semester of the MSc in Data Analytics program. This repository contains the CA1 assignment guidelines from the college and my submission. To see all original commits and progress, please visit the original repository using the link below.

A quantitative measure of disease progression one year after baseline

A Image classification CNN model with more than 85% accuracy. An interactive API is been designed using flask framework for better user experience. Techniques like batch normalization, dropouts is used for improved accuracy.

To provide a complete pipeline to develop a deep learning model. More specifically, a multiclass classification (single label) deep learning model that can predict what stage of Alzheimer's a patient is, from their MRI image

Recurrent neural network with GRUs for trigger word detection from an audio clip

A simple study on how to use Tensorflow platform (without Keras) for a simple number classification task using a Neural Network.

This GitHub repository explores the importance of MLP components using the MNIST dataset. Techniques like Dropout, Batch Normalization, and optimization algorithms are experimented with to improve MLP performance. Gain a deeper understanding of MLP components and learn to fine-tune for optimal classification performance on MNIST.

in this repo, you will find implementation of various classification models, data augmantation ,cnn designing and model reguralization

This project implements a CNN-based Face Mask Detection Model to classify images as with mask or without mask. Trained on a labeled dataset, the model achieves 90% accuracy, making it suitable for real-world applications like public safety monitoring.

The primary objective of this project is to design and train a deep neural network that can generalize well to new, unseen data, effectively distinguishing between rocks and metal cylinders based on the sonar chirp returns.

A NumPy-based implementation of neural networks from scratch, covering core components like forward and backward propagation, activation functions, loss functions, and optimizers, inspired by the "Neural Networks from Scratch" book.

Next Word Prediction App built using deep learning. The project uses LSTM and GRU models trained on textual data to predict the next most probable word given an input sequence. A Streamlit web app allows users to dynamically select the model and interactively generate predictions in real time.

A modular neural network implemented from scratch in Python. Includes customizable architecture, training with backpropagation, evaluation metrics, and visualizations using the EMNIST dataset.

The aim was to develop a robust Convolutional Neural Network (CNN) for accurately classifying handwritten digits from the MNIST dataset

Deep Learning project about the design and training of a model for Image Classification

I have trained a CNN model on Dog and Cat Image dataset. This model predicts whether the given image is of Cat or Dog.