Unsupervised Depth Perception
This episode is an interview with Tinghui Zhou. In the recent paper "Unsupervised Learning of Depth and Ego-motion from Video", Tinghui and collaborators propose a deep learning architecture which is...
26 Touko 201723min
[MINI] Convolutional Neural Networks
CNNs are characterized by their use of a group of neurons typically referred to as a filter or kernel. In image recognition, this kernel is repeated over the entire image. In this way, CNNs may achi...
19 Touko 201714min
Multi-Agent Diverse Generative Adversarial Networks
Despite the success of GANs in imaging, one of its major drawbacks is the problem of 'mode collapse,' where the generator learns to produce samples with extremely low variety. To address this issue, t...
12 Touko 201729min
[MINI] Generative Adversarial Networks
GANs are an unsupervised learning method involving two neural networks iteratively competing. The discriminator is a typical learning system. It attempts to develop the ability to recognize members of...
5 Touko 20179min
Opinion Polls for Presidential Elections
Recently, we've seen opinion polls come under some skepticism. But is that skepticism truly justified? The recent Brexit referendum and US 2016 Presidential Election are examples where some claims t...
28 Huhti 201752min
OpenHouse
No reliable, complete database cataloging home sales data at a transaction level is available for the average person to access. To a data scientist interesting in studying this data, our hands are com...
21 Huhti 201726min
[MINI] GPU CPU
There's more than one type of computer processor. The central processing unit (CPU) is typically what one means when they say "processor". GPUs were introduced to be highly optimized for doing floatin...
14 Huhti 201711min
[MINI] Backpropagation
Backpropagation is a common algorithm for training a neural network. It works by computing the gradient of each weight with respect to the overall error, and using stochastic gradient descent to iter...
7 Huhti 201715min
