Machine Learning: Overview
"The term machine learning refers to the automated detection of
meaningful patterns in data."
Machine Learning: Deep Learning
Research into neural networks began in the 50s with the concept of emulating a neuron by summing a set of weighted inputs, with a response being triggered if the combined values exceeded a threshold. This was known as a Perceptron. A perceptron is a single-layer neural network.
Deep Learning refers to the use of neural networks that are more than one layer deep.
Machine Learning: TensorFlow
This brought things a bit more down to earth with the focus on a particular software implementation of machine learning algorithms.
This topic probably comes closest to something I'd be able to apply at work. As I mentioned earlier, there was not a very strong lineup of Big Data topics.
TensorFlow uses GPGPU (General-purpose computing on graphics processing units) to accelerate processing. I was aware that bitcoin mining software did this but this was the first time I saw this acronym or really became aware that GPGPU was being used for a lot of other things. This is your excuse for getting a really expensive, top-of-the-line graphics card. If we start applying machine learning algorithms at work, my guess is we will build on top of Spark MLib since we already have such a big investment in the Hadoop, Scala, Spark stack. It's weird that Brian didn't mention this at all.
There's a JavaScript API called TensorFlowJS that allows you to run ML in your browser! Your phone! IOT devices! And here's another thing you can debug in Chrome DevTools.
Links
- A visual introduction to machine learning
- Keras: The Python Deep Learning library
- Dl4j Deep Learning for Java
- TensorFlow.js
- scikit-learn: Machine Learning in Python
- Brian Sletten's Data Science and Machine Learning resources
- Vulkan
- Welcome to the Jungle Or, A Heterogeneous Supercomputer in Every Pocket
- Doing Data Science
- The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World
- The Theory That Would Not Die: How Bayes' Rule Cracked the Enigma Code, Hunted Down Russian Submarines, and Emerged Triumphant from Two Centuries of Controversy
- Machine Learning with R ("Make sure you get the second edition")
- Deep learning with Python
- Perceptrons by Marvin Minsky (downloadable)
A few miscellaneous comments about the show in general...
Women are definitely better represented than in the bad old days. I would say the percentage of women has increased from around 5% to 20 or 25%.
The Mac is still a popular choice and I didn't notice anyone else running Linux.
Ditch Gradle, maybe reconsider the whole corporate sponsorship thing.
Women are definitely better represented than in the bad old days. I would say the percentage of women has increased from around 5% to 20 or 25%.
The Mac is still a popular choice and I didn't notice anyone else running Linux.
Ditch Gradle, maybe reconsider the whole corporate sponsorship thing.
No comments:
Post a Comment