David Rawlinson on This is the second part of our comparison between convolutional competitive learning and convolutional or fully-connected sparse autoencoders. To understand our motivation for this comparison, have a look at the first article. We decided to compare two specific algorithms that tick most of the fe ...
Read More David Rawlinson on Competitive learning is a branch of unsupervised learning that was popular a long, long time ago in the 1990s. Older readers may remember - the days before widespread use of GSM mobile phones and before Google won the search engine wars! Although competitive learning is now rarely used, it is worth ...
Read More
Abdelrahman Ahmed on Eager Execution is an imperative, object oriented and more Pythonic way of using TensorFlow. It is a flexible machine learning platform for research and experimentation where operations are immediately evaluated and return concrete values, instead of constructing a computational graph that is executed later.
Read More David Rawlinson on We've just uploaded a spin-off research paper to arXiv titled "Sparse Unsupervised Capsules Generalize Better". So what's it all about? Capsules Networks You may have heard of Capsules Networks already - if not, have a read of one of these blog articles (here, here, here, or here (EM routing)), ...
Read More
Gideon Kowadlo on The dataset is an integral part of an ML engineer’s toolkit. We recently compiled useful information about a range of these well known datasets. It’s all in one place, and hopefully useful to others as well.
Read More Gideon Kowadlo on ML Today Today’s Machine Learning has demonstrated unprecedented performance in what seems like every application thrown at it. Almost all the success has been based on advanced memory systems that can learn to recognise an input based on a large number of training examples. This is the equiv ...
Read More Gideon Kowadlo on 2018 is a fresh new year and an exciting milestone for Project AGI. Dave and I have been discussing, dreaming, playing around with and striving towards general purpose AI for over 6 years. It started with musings on the algorithmic underpinnings of consciousness and the nature of intelligence. ...
Read More Abdelrahman Ahmed on There are plenty of established machine learning frameworks out there, and new frameworks are popping up frequently to address specific niches. We were interested in examining if one of these frameworks fits in our workflow. I surveyed the most popular frameworks, and aim to provide a helpful comparative analysis.
Read More Abdelrahman Ahmed on SVHN is relatively new and popular dataset, a natural next step to MNIST and complement to other popular computer vision datasets. This is an overview of the common preprocessing techniques used and the best performance benchmarks, as well as a look at the state-of-the-art neural network architectures used.
Read More Abdelrahman Ahmed on Releasing a set of tools for converting the Street View House Numbers (SVHN) dataset into images with additional preprocessing options such as grayscaling.
Read More
