This repo contains the codes, reports, datasets and question papers for the assignments in the course CS671 Deep Learning & Applications 2022 February-May Semester at Indian Institute of Technology, Mandi. Syllabus • Moodle
- Implementation of Perceptron from scratch for classification tasks view
- Implementation of Fully Connected Neural Network (FCNN) with one hidden layer from scratch for classification tasks view
- Implementation of Fully Connected Neural Network (FCNN) with two hidden layer from scratch for classification tasks view
- Implementation of Perceptron from scratch for regression tasks view
- Implementation of Fully Connected Neural Network (FCNN) with one hidden layer from scratch for regression tasks view
- Implementation of Fully Connected Neural Network (FCNN) with two hidden layer from scratch for regression tasks view
Perceptron & FCNN Report view • Question Paper open • Dataset download
- FCNN with 3 hidden layers using cross entropy loss by stochastic gradient descent (SGD) algorithm view
- FCNN with 3 hidden layers using cross entropy loss by vanilla gradient descent algorithm view
- FCNN with 3 hidden layers using cross entropy loss by SGD with momentum (NAG) view
- FCNN with 3 hidden layers using cross entropy loss by RMSProp algorithm view
- FCNN with 3 hidden layers using cross entropy loss by Adam optimizer view
- One hidden layer autoencoder for compression view
- Three hidden layer autoencoder for compression view
- One hidden layer autoencoder for classification task view
- Three hidden layer autoencoder for classification task view
- Denoising Autoencoder view
Optimizers and Autoencoders Report view • Question Paper open • Dataset download
- 2 dimensional convolution (with zero padding & stride) from scratch view
- Building Convolutional Layers view
- Building Network and Backpropagation view
- Using Builtin functions view
- GradCAM - Visualization of the Influence of Input Pixels view
- VGG19 Model view
- Visualizing the patches that maximally activate a neuron (VGG16) view
Convolutional Neural Network Report view • Question Paper open • Dataset download
RNN and LSTM report view • Question Paper open • Dataset download
- Tutorial I: Introduction to keras, DNNs & Autoencoders in keras
- Tutorial II: CNNs: Plotting Feature maps, kernels, Transfer learning, Visualisation of patches maximally activate a neuron see
- Tutorial III: RNNs & LSTMs: Passing variable length inputs, more