はてなブックマーク

ICLR is a relatively new conference that is primarily concerned with deep learning and learned representations. The conference is into its third year and had over 300 attendees, two of which were from Lyst. In this post we’ll discuss a few of the interesting papers and themes presented this year. Simplifying network topology One of the difficulties of employing deep convolutional networks is that

Discuss this post on Hacker News Word embeddings are ways of mathematically representing natural language words in a manner that preserves the semantic and syntactic similarities between them. This is accomplished through representing words as high-dimensional vectors: the spatial relationship between these embeddings then represent the relationships between words. For example, the representations

The OpenRoss image proxy service provides a way of serving dynamically resized images from Amazon S3 in a way that is fast, efficient, and auto-scales with traffic. We have hosted the source for this service at Github. Motivation At Lyst we scrape, and have scraped, millions of products that all have at least one image. In our infancy, we saved all product images with 10 preset sizes, and then ren

Bayesian A/B Test Calculator The Beta-Bernoulli model in the context of A/B testing. Need Help? See here or read more about Bayesian inference in A/B testing at our blog. Made at Lyst Find this on Github TL:DR; Instructions 1Specify the prior alpha and beta parameters. 2Plot the priors and revise parameters as necessary. 3Enter data on the number of successes and failures in the test and control g

Click here if you are looking for our interactive A/B testing inference machine. Otherwise, read on! A/B testing is an excellent tool for deciding whether or not to go ahead with rolling out an incremental feature. To perform an A/B test, we divide users randomly into a test and control group, then serve the new feature to the test group while the control group continues to experience the current

Some of these colors can be deciphered by a human but all are very difficult for a computer. Even simple colors such as snakeskin or periwinkle can be hard to process automatically. In the past, we used a range of techniques to map retailer colors to lyst colors, from simple keyword matching to complex ML models. We found that these methods produced unsatisfactory results due to complexity of colo

At Lyst we process a lot of products from a lot of retailers. However, the product information we get from retailers isn’t the same across the industry as: Retailers may categorise products differently to competitors, Retailers may not provide every bit of information that we need, Retailers may have large catalogues and use vague auto-generated descriptions. Due to this, we have to ensure that ea