Machine Learning and Deep Learning course coding Homeworks NYCU Taiwan

• Image Recognition using Convolutional Neural Network
• Dataset MNIST and CIFAR10
• Showing correctly classified and miss classified Images
• Displaying 9 feature maps per convolutional layer
• Effect of L2 Regularization on overfittng and accuracy
• Building a recurrent neural network for character-level language model
• Recurrent neural network (RNN) for word generation using character-level language model
• Long short term memory (LSTM) for word generation using charater-level language model
• Shakespeare dataset
• Regression using Neural Network with 2 Hidden Layers from scratch
• Classification using Neural Network with one Hidden layer from scratch
• Regularized linear regression (polynomial basis) using LSE and Newton's method and visualization
• MNIST Digit classification using Naive Bayes that support discrete and continous feature of MNIST data
• Online learning to learn the beta distribution of the parameter p (chance to see 1) of the coin tossing trails in batch
• Random Data Generator
• Sequential Estimator
• Baysian Linear regression
• Support Vector Machine to tackle classification of MNIST data using LIBSVM library
• kernel functions used (linear, polynomial, and RBF kernels)
• Find out support vectors using 2D Dataset
• Implementation of k-means clustering, kernel k-means, spectral clustering, DBSCAN using Numpy from scratch
• Dataset: 2 datasets with points on 2d space, circle.txt and moon.txt
• Different ways to do dimension reduction on MNIST data using PCA, LDA, S-SNE and T-SNE
• Use PCA to show the first 25 eigenfaces using att_faces dataset
• Logistic Regression from scratch
• Random data generator
• EM Algorithm from scratch
• Dataset: MNIST Data