Skip to content

Repository files navigation

Deep-Learning-Lab

This repository contains code written during the Advanced Machine Learning (Deep Learning) lab. The experiments were assigned by the lab professor and cover various topics within deep learning. The implementations primarily use TensorFlow and Python in Jupyter notebooks.

Experiment 1 Aim: Basic Concept of Tensor This experiment introduces the fundamental concepts of tensors, including their creation, manipulation, and basic operations.

Experiment 2 Aim: Basic Programs on Tensor This experiment involves writing basic programs to understand tensor operations in TensorFlow.

Experiment 3 Aim: Logistic Regression for Binary Classification with Core APIs Implementation of logistic regression for binary classification using TensorFlow's core APIs.

Experiment 4 Aim: The Sequential Model Introduction to the Sequential model in TensorFlow, demonstrating how to build and compile a model using this API.

Experiment 5 Aim: Design a Sequential Layer By Implementing The Dataset Pet Finder Mini

Normalize the dataset Divide it into training and testing sets Calculate accuracy score and loss rate

Experiment 6 Aim: Implement Convolutional Neural Network Architecture on Chest X-Ray Dataset

Extract features Evaluate accuracy, specificity, sensitivity, F1-score Visualize the area under the curve (AUC) for the model

Experiment 7 Aim: Implement a Pre-Trained Model on Chest X-Ray Dataset

Extract features Evaluate accuracy, specificity, sensitivity, F1-score Visualize the area under the curve (AUC) for the model

Experiment 8 Aim: Implement a Recurrent Neural Network on any Time Series Dataset Write a program to build and train a recurrent neural network for time series forecasting or analysis.

Experiment 9 Aim: Implement LSTM using RNN on Breast Cancer Dataset Write a program to build and train an LSTM model for predicting breast cancer using RNN.

Experiment 10 Aim: Implement a GAN on Fashion MNIST Dataset to Identify Fake or Real Image Write a program to build and train a Generative Adversarial Network (GAN) to distinguish between fake and real images in the Fashion MNIST dataset.

About

Codes Written By Me During The Advanced Machine Learning (Deep Learning ) Lab

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages