This project contains notebooks that provides a comprehensive introduction to various deep learning techniques, from basic neural networks to advanced convolutional neural networks (CNNs), and their applications in real-world problems
These notebooks are created as assignments while I am taking a course on Coursera
Skills -> Computer Vision, Image Classification, Deep Neural Network, Convolution, Pooling, Activation, Optimizer, Loss function, Tensorflow, Keras, Python
Included Notebooks:
- SLNN-House-Prices-Prediction
- This model predicts house prices based on the number of bedrooms using linear regression
- Neural-Network-Image-Classification
- This model trains a neural network to classify Fashion MNIST into 10 categories using a feedforward architecture with one hidden layer
- Speeding-Neural-Network-With-Convolution
- This CNN model effectively leverages convolutional and pooling layers for building efficient, scalable, and robust neural networks for multi-classifaction of huge image dataset
- CNN-Happy-Sad-Image-Classification
- This model features a CNN for binary image classification (happy/sad) with three convolutional layers, ReLU activation, and max pooling, followed by a dense layer and sigmoid output. It uses the Adam optimizer and binary cross-entropy loss, with early stopping based on accuracy