Welcome to my repository featuring a comprehensive collection of PyTorch implementations showcasing various deep learning algorithms. Here's a concise overview of each notebook:
This notebook demonstrates the implementation of an Artificial Neural Network (ANN) using PyTorch. Explore its application on the diabetes dataset, witnessing its effectiveness in handling complex data patterns. This notebook leverages Dense layer with ReLU activation, Adam optimizer, Cross entropy loss and trains the model for 5000 epochs.
Experience the power of Convolutional Neural Networks (CNNs) through this PyTorch implementation, focusing on image classification using the MNIST dataset. Witness the network's ability to extract meaningful features from images. This notebook showcases the use and implemetation of convolution layers with a neural network. A flatten layer takes the features extracted by the convolutional layers and feed it to an ANN.
Explore Generative Adversarial Networks (GANs) through this PyTorch implementation. Gain insights into how GANs operate, particularly in generating realistic data distributions, with a focus on dense neural networks.
This notebook delves into Long Short-Term Memory (LSTM) networks using PyTorch. Witness how LSTMs excel in capturing long-term dependencies in sequential data, making them ideal for tasks such as time series prediction.
To understand the basic neural networks one should know about logistic regression. Implementing logistic regression with pytorch is good enough to demonstarte the use of dense layers along with activation functions in pytorch.
Explore Recurrent Neural Networks (RNNs) in the context of name recognition using PyTorch. Witness how RNNs excel in processing sequential data and making predictions, making them suitable for tasks like text generation.
Dive deeper into Recurrent Neural Networks (RNNs) with a focus on the MNIST problem. Gain practical insights into leveraging RNNs for sequential data processing tasks, particularly in the context of handwritten digit recognition.
Explore the transformative architecture of Transformers through our PyTorch implementation. Understand how Transformers have revolutionized various natural language processing tasks, such as machine translation and text generation.
Delve into sequence-to-sequence learning with our PyTorch implementation. Gain a comprehensive understanding of how this paradigm enables tasks like language translation and summarization.
Embark on a journey of discovery as you explore these fundamental and advanced deep learning algorithms implemented with PyTorch. Let's delve into the world of artificial intelligence together.