I gave an overview on bloom filter in the previous blog post. But if I summarize the properties of bloom filter as a data structure;

Can several wrongs make a right? While it may seem counter-intuitive, this is possible, sometimes even preferable, in designing predictive models for complex problems such as crime prediction.

Myth #10: Everybody should abandon (conda | pip) and use (pip | conda) instead!¶

In the previous post, we saw how the backprop algorithm itself is a bottleneck in training, and how the Synthetic Gradient approach proposed by DeepMind reduces/avoids network locking during training. While very clever, there is something unsettling about the solution. It seems very contrived, and definitely resource intensive.  For example, a simple feed forward network under the scheme has a Rube-Goldbergesque feel to it.

Here is the 1st batch of results from the Becoming a Data Scientist Survey. Because of the sample size and unscientific casual nature of this survey, we can’t make any broad generalizations about the industry from these results, but you can see some general preliminary trends in the breakdowns that would be interesting to study more.

The fast and easy guide to the most popular Deep Learning framework in the world.

You’re a hotshot manager. You love your dashboards and you keep your finger on the beating pulse of the business. You take pride in using data to drive your decisions rather than shooting from the hip like one of those old-school 1950s bosses. This is the 21st century, and data is king. You even hired a sexy statistician or data scientist, though you don’t really understand what they do. Never mind, you can proudly tell all your friends that you are leading a modern data-driven team. Nothing can go wrong, right? Incorrect. If you don’t pay attention, data can drive you off a cliff. This article discusses seven of the ways this can happen. Read on to ensure it doesn’t happen to you.