Rants by ABLL

This is where I exercise my communication skills and pretend as if I know something about computer vision/machine learning. I aim for subjectivity over correctness in an attempt to distance myself from boring articles. Go ahead and subscribe to the Atom feed.

Introducing CUDArray

08 November 2014
Introducing CUDArray

Neural networks and deep learning are booming (still). Quite a few software frameworks have appeared over the last year, though none that allow high-level Python/NumPy programming with fast underlying array operations. In this post, I present my attempt at making the two ends meet. CUDArray is a CUDA-accelerated subset of the NumPy library with support for neural networks as its primary goal.

FFT-based convolutional neural networks

14 July 2014

A few weeks ago, I decided to implement my own convolution operations for the GPU. My motivation was the need for an implementation that could be easily modified. Unfortunately, most implementations available online are either slow or a big mess code-wise:

A simple implementation of convolutional neural networks

22 May 2014

I was recently asked for a simple implementation of a convolutional neural network (CNN). The purpose was to allow GPU-savvy programmers to understand the problem by inspecting the code; and to serve as reference for their optimized implementation. This request reignited a frustration from when I myself started looking into CNNs a couple of months ago: There are no easily read implementations available! Most CNN implementations are either highly optimized GPU code or contain only barebone operations in a non-modular code structure. In either case, the code is hard to read and the back-propagation algorithm is difficult to recognize.

Hello brave new world

25 April 2014

After months of rumination, I have finally converged to a good personal website solution. As it turned out, the toughest part was to choose the right frameworks! At first, I was reluctant to use the popular Jekyll (I'm not a Ruby programmer) in favor of the Python-based Pelican. However, Jekyll and its surrounding ecosystem is more mature and I have not run into limitations like I did with my initial attempt using Pelican.