We are preparing for the second edition of our PyTorch-based Deep Learning for NLP training. It’s a two-day affair, crammed with a lot of learning and hands-on model building where we get to play the intricate dance of introducing the topics from the ground up while still making sure folks are not far from the state-of-the-art. Compared to our first attempt at NYC this year, we are adding new content, changing existing content to explain some basic ideas well. One subtopic I am quite excited to add is a discussion of “When to use Deep Learning for NLP and when not to”. This post will be expanding on that.
Inferring data loss (and correcting for it) from fundamental relationships
I recently analyzed a somewhat puzzling data set. I was sending HTTP POST requests to a system. The system’s would then acknowledge receipt of these requests (returning a 200 status code), and some time later (it was a slow asynchronous process) send a web hook to a specified URL if the request was successful. However, successful was far from certain; most requests actually failed. My job was to measure the success rate.
The Advent of Analytics Engineering
Data Science has become an exploding field in recent years, and depending on whether you are focusing on machine learning, artificial intelligence, or citizen data science, the discipline of data science is creating very high expectations.
Crosslingual document comparison
How much compute do we need to train generative models?
Update (09/01/17): The post is written to be somewhat silly and numbers are not meant to be accurate. For example, there is a simplifying assumption that training time scales linearly with the # of bits to encode the output; and 5000 is chosen arbitrarily given only that the output’s range has 65K3 dimensions and each takes one of 256 integers.*
A.I. 'Bias' Doesn't Mean What Journalists Say It Means
In Florida, a criminal sentencing algorithm called COMPAS looks at many pieces of data about a criminal and computes the probability that they will commit new crimes. Judges use these risk scores in criminal sentencing and parole hearings to determine whether the offender should be kept in jail or released.
Poor Customer Support?
 |
My blog is currently hosted by GoDaddy. I’ve been using them now for almost a decade.Most of the time, I have no complaints (though they do have a habit of calling every six months or so to make sure “everything is OK”, but this is really just a thinly veiled attempt to get me to re-subscribe early for another yearly plan to stop me churning, I get this, they are running a business. If I’ve time, I’ll take the call as they usually offer a discount to continue; it’s a Quid Pro Quo trade).However, the true test of customer service is how a company behaves when something goes wrong. Today GoDaddy really dropped the ball on this one, and they really aren’t interested in picking it up. |
The jet plane that shot itself down
 |
All war is tragic. Friendly fire, sometimes referred to as a blue on blue incidents, or fratricide, whilst becoming rarer with advances in technology,* is equally as tragic.Then there are the cases of self-inflicted harm (not all these incidents occur during war time):More precision and accuracy of weaponry, better intelligence, electronic marking of *Friend-or-Foe … |
Python Deep Learning tutorial： Create a GRU (RNN) in TensorFlow
MLPs (Multi-Layer Perceptrons) are great for many classification and regression tasks. However, it is hard for MLPs to do classification and regression on sequences. In this Python deep learning tutorial, a GRU is implemented in TensorFlow. Tensorflow is one of the many Python Deep Learning libraries.
Designing a Deep Learning Project
There are numerous on-line and off-line technical resources about deep learning. Everyday people publish new papers and write new things. However, it is rare to see resources teaching practical concerns for structuring a deep learning projects; from top to bottom, from problem to solution. People know fancy technicalities but even some experienced people feel lost in the details, once they need to structure their own project.