Applied-Deep-Learning

Welcome to the Applied-Deep-Learning repository. This project showcases practical implementations and experiments in deep learning, demonstrating the application of advanced techniques to real-world problems. It includes various models, code examples, and projects across different domains such as computer vision, natural language processing, and general AI.

Overview

This repository is designed to illustrate the practical applications of deep learning techniques, including:

• Deep Learning Architectures: Implementations of Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and other neural network models.
• Real-World Applications: Practical examples applied to tasks such as image classification, sentiment analysis, and sequence modeling.
• Pre-trained Models: Utilization of transfer learning and pre-trained models to enhance learning efficiency.
• Data Handling: Methods for preprocessing and analyzing data to ensure robust training and evaluation of models.

Features

• CNN Coding: Exercises and implementations related to Convolutional Neural Networks.
• RNN Experiments: Various applications of Recurrent Neural Networks for different tasks.
• Generative AI Projects: Work on Generative Adversarial Networks (GANs) for generating images and other applications.
• Neural Network Models: Examples demonstrating different neural network models and their uses.
• Group Project: Collaborative work and research on advanced topics in deep learning.

Folder Structure

Here's a brief overview of the repository’s structure:

Folder/Directory	File Name	Description
Basics	Activation_functions.ipynb	Covers activation functions used in neural networks.
	Normal_equation.ipynb	Explains the normal equation method for linear regression.
	Regression.ipynb	Demonstrates various regression techniques.
	RegressionDemo_QuadEq.ipynb	Provides a demonstration of regression applied to quadratic equations.
CNN_coding	CNN_class_exercises_comments.ipynb	Exercises on CNNs with explanation.
	FastAiDemo_comments.ipynb	CNN implementation using FastAI with detailed commentary.
	transfer-learning-with-xception-for-cifar-10-final_comments.ipynb	Transfer learning example with the Xception model for CIFAR-10, including explanation.
Gen AI	Anime-GANs.ipynb	Explores GANs for generating anime-style images.
GroupProject	Group_Project_06_.pdf	Summary of group project findings.
	RA_Working_Binary_IMDB.ipynb	Binary classification using the IMDB dataset.
	RA_Working_Binary_Synthetic_Data.ipynb	Binary classification with synthetic data.
	RA_Working_MultiClass_Reuters.ipynb	Multi-class classification with the Reuters dataset.
	Ring Attention with Blockwise Transformers for Near-Infinite Context.pdf	Research on advanced transformer models for extensive context handling.
NeuralNetwork Models_coding	Boston_Housing_simple_HousePricePredictions.ipynb	Simple regression for predicting house prices.
	Classifying_movie_reviews+Newswire_Multiclass.ipynb	Binary classification and Multi-class classification for movie reviews and newswire data.
	MNIST_classifier_simple.ipynb	Multi-class classification of handwritten digits using MNIST.
	Mathematical-Building-Blocks.ipynb	Foundations and mathematical principles of neural networks.
	Number_of_parameters_in_a_fcNN.ipynb	Analysis of parameter counts in fully connected neural networks.
RNN	rnn_MNIST.ipynb	Classification of MNIST digits using RNNs.
	rnn_imdb_reviews.ipynb	Sentiment analysis of IMDB reviews with RNNs.
	rnn_lstm_seq2seq.ipynb	Sequence-to-sequence models using LSTM networks.
	rnn_np_v2_NumPy implementation.ipynb	NumPy-based RNN implementation.
	rnn_with_keras.ipynb	RNN implementation using Keras.

Thank You. Let’s keep learning and growing together!