Convolutional Neural Network brings several breakthroughs for supervised tasks in Computer Vision and other visual problems in Artificial Intelligence. Moreover, semi-supervised or unsupervised learning has remarkable milestones in attempts to understand how models work. These insights unfold impressive studies which utilitize pre-trained models to extract deep-learning-based features or solve various tasks. This post introduces Artistic… Continue reading Neural Algorithm of Artistic Style Transfer: Understanding with PyTorch examples
Category: Practice
Principle component analysis (PCA) example: Experiments with Iris Dataset
This article shows practising PCA with Iris dataset. More detail about PCA, read the post Principal Component Analysis. Preparation Import libraries Load and visualize the dataset Convert data to numpy array. x has shape (150, 4), corresponding to observation in rows and variables in columns. Compute PCA Calculate the covariance matrix. Besides np.cov of numpy,… Continue reading Principle component analysis (PCA) example: Experiments with Iris Dataset
Digit Recognizer in Kaggle
This article presents how I personally utilize the Convolutional Neural Network to build a model solving a typical long-standing problem: Digit Recognizer. 1. Explore Data Kaggle provides MNIST Dataset for this challenge. It has 42000 images with labels for training and 28000 images without labels for testing. Each image is a 28x28 grayscale picture (figure… Continue reading Digit Recognizer in Kaggle


