Digests » 63

ai

Making Convolutional Networks Shift-Invariant Again

odern convolutional networks are not shift-invariant, as small input shifts or translations can cause drastic changes in the output. Commonly used downsampling methods, such as max-pooling, strided-convolution, and average-pooling, ignore the sampling theorem. The well-known signal processing fix is anti-aliasing by low-pass filtering before downsampling. However, simply inserting this module into deep networks degrades performance; as a result, it is seldomly used today. We show that when integrated correctly, it is compatible with existing architectural components, such as max-pooling and strided-convolution.

A guide to Web Scraping without getting blocked

Web scraping or crawling is the fact of fetching data from a third party website by downloading and parsing the HTML code to extract the data you want.

Neural Networks From Scratch

This 4-post series, written especially with beginners in mind, provides a fundamentals-oriented approach towards understanding Neural Networks. We’ll start with an introduction to classic Neural Networks for complete beginners before delving into two popular variants: Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs).

Machine Learning for Creativity and Design

Generative machine learning and machine creativity have continued to grow and attract a wider audience to machine learning. Generative models enable new types of media creation across images, music, and text - including recent advances such as StyleGAN, MuseNet and GPT-2. This one-day workshop broadly explores issues in the applications of machine learning to creativity and design.

How I built a spreadsheet app with Python to make data science easier

About a year ago I started tinkering with the idea of building the data science IDE that I had always wanted. Having worked extensively with Microsoft Excel, R (Studio) and Python, I envisioned how some integrated version of those would make my life easier.