How to Build Your Own Blockchain Part 2 — Syncing Chains From Different Nodes
Welcome to part 2 of the JackBlockChain, where I write some code to introduce the ability for different nodes to communicate.
Multi Armed Bandit
||
AlphaGo Zero: Minimal Policy Improvement, Expectation Propagation and other Connections
This is a post about the new reinforcement learning technique that enables AlphaGo Zero to learn Go from scratch via self-play. The paper has been out for a week I guess it’s now considered old - sorry for the latency.
COLT 2018 call for papers
Sebastien Bubeck
发表于
Philippe Rigollet and myself will be the program chairs for this year’s edition of COLT. It will be in Stockholm in July, which I hear is absolutely gorgeous at that time of the year. We also have a fantastic lineup of invited speakers: Stephane Mallat, Susan Murphy, and Johan Hastad. We believe we will also guarantee high quality reviews for your submissions as we have assembled a great (and extended) program committee to make sure that we cover all aspects of modern learning theory (in particular we expect the number of subreviewers to be minimal). See below for the PC, as well as the call for papers. Looking forward to read all your submissions in February!
AWS Machine Learning Big Data NYC
My slides on AWS Machine Learning platform at the Global Big Data conference - NYC 2017 Oct 24.
Online Hard Example Mining on PyTorch
Online Hard Example Mining (OHEM) is a way to pick hard examples with reduced computation cost to improve your network performance on borderline cases which generalize to the general performance. It is mostly used for Object Detection. Suppose you like to train a car detector and you have positive (with car) and negative images (with no car). Now you like to train your network. In practice, you find yourself in many negatives as oppose to relatively much small positives. To this end, it is clever to pick a subset of negatives that are the most informative for your network. Hard Example Mining is the way to go to this.
Hard Examples Mining in Keras
In deep learning, one often works with a high-level interface of a particular framework. No need for computing gradients manually, just stack layers with your favorite Keras.
JUnit,Integration,End to End Tests
During my experience I meet many definition of Test Types.I know them by many names : end to end tests, functional test, system test, UI test, Selenium Tests, Soap-UI test, Integration tests,Acceptance tests.
Some Thoughts on Meditation
contact@andreykurenkov.com
发表于
I’ve had a rough few months. Work, work, work, a failed research project, broken laptops, moving, PhD applications, financial mishaps… it’s been a stressful time. Bummer. But, it’s not big deal, this too shall pass, etc - the bummerness of the situation is not the point. The point is that as has happened before and will happen again, this current tired predicament has given me motivation to take up something I have been meaning to do for a while: writing about meditation.