Deep Learning has shown very promising results in the field of Computer Vision. But when applying it to practical domains such as medical imaging, lack of labeled data is a major challenge.

In practical settings, labeling data is a time consuming and expensive process. Though, you have a lot of images, only a small portion of them can be labeled due to resource constraints. In such settings, how can we leverage the remaining unlabeled images along with the labeled images to improve the performance of our model? The answer is semi-supervised learning.

FixMatch is a recent semi-supervised approach by Sohn et al. from Google Brain that improved the state of the art in semi-supervised learning(SSL). It is a simpler combination of previous methods such as UDA and ReMixMatch. In this post, we will understand the concept of FixMatch and also see how it got 78% median accuracy and 84% maximum accuracy on CIFAR-10 with just 10 labeled images.

Natural language processing algorithms applied to three million materials science abstracts uncover relationships between words, material compositions and properties, and predict potential new thermoelectric materials.

The overwhelming majority of scientific knowledge is published as text, which is difficult to analyse by either traditional statistical analysis or modern machine learning methods. By contrast, the main source of machine-interpretable data for the materials research community has come from structured property databases, which encompass only a small fraction of the knowledge present in the research literature. Beyond property values, publications contain valuable knowledge regarding the connections and relationships between data items as interpreted by the authors. To improve the identification and use of this knowledge, several studies have focused on the retrieval of information from scientific literature using supervised natural language processing, which requires large hand-labelled datasets for training. Here we show that materials science knowledge present in the published literature can be efficiently encoded as information-dense word embeddings (vector representations of words) without human labelling or supervision. Without any explicit insertion of chemical knowledge, these embeddings capture complex materials science concepts such as the underlying structure of the periodic table and structure–property relationships in materials. Furthermore, we demonstrate that an unsupervised method can recommend materials for functional applications several years before their discovery. This suggests that latent knowledge regarding future discoveries is to a large extent embedded in past publications. Our findings highlight the possibility of extracting knowledge and relationships from the massive body of scientific literature in a collective manner, and point towards a generalized approach to the mining of scientific literature.

In this post we’ll explore how we can derive logistic regression from Bayes’ Theorem. Starting with Bayes’ Theorem we’ll work our way to computing the log odds of our problem and the arrive at the inverse logit function. After reading this post you’ll have a much stronger intuition for how logistic

If you're a web developer, you've probably had to make a user account system. The most important aspect of a user account system is how user passwords are protected. User account databases are hacked frequently, so you absolutely must do something to protect your users' passwords if your website is ever breached. The best way to protect passwords is to employ salted password hashing. This page will explain why it's done the way it is.

There are a lot of conflicting ideas and misconceptions on how to do password hashing properly, probably due to the abundance of misinformation on the web. Password hashing is one of those things that's so simple, but yet so many people get wrong. With this page, I hope to explain not only the correct way to do it, but why it should be done that way.