Deep learning for complete beginners: Using convolutional nets to recognise images by …

Upcoming Course Welcome to the second in a series of blog posts that is designed to get you quickly up to speed with deep learning; from first principles, all the way to discussions of some of the intricate details, with the purposes of achieving respectable performance on two established machine learning benchmarks: MNIST (classification of handwritten digits) and CIFAR-10 (classification of small images across 10 distinct classes—airplane, automobile, bird, cat, deer, dog, frog, horse, ship & truck). MNIST CIFAR-10 Last time around, I have introduced the fundamental concepts of deep learning, and illustrated how models can be rapidly developed and prototyped by leveraging the Keras deep learning framework. Ultimately, a two-layer multilayer perceptron (MLP) was applied to MNIST, achieving an accuracy level of $98.2%$, which can be quite easily improved…


Link to Full Article: Deep learning for complete beginners: Using convolutional nets to recognise images by …