- Contains homeworks from Deep Learning class of METU CENG
Homeworks are partly adapted from Stanford's cs231n class.
-
Task 1 : SVM exercise (implement SVM loss, lr tuning and regularization, optimize with SVM, visiulizing weights)
-
Task 2 : Softmax exercise (implement softmax loss, lr tuning and regularization, optimize with softmax, visiulizing weights)
-
Task 1 : Implementing a two layer neural network
-
Task 1 : Neural Net for regression (Estimating blood pressure from PPG signal)
-
Task 1 : Modular neural networks (optimizing the implementation)
-
Task 2 : Training a convolutional network
-
Task 3 : Image gradients and Saliency maps
-
Task 4 a : Neural Net for regression (Estimating blood pressure from PPG signal)
-
Task 4 b : Image generation from gradients
-
Task 5 : Estimating blood pressure with CNN architecture
-
Task 1 : Image Captioning with RNNs
-
Task 2 : Image Captioning with LSTMs
-
Task 3 : Denoising Autoencoder implementation
-
Task 4 : (Optional) Image Captioning with GRUs with GRU basics