- Ask HN: What do people use to prevent crawlers? | Hacker News –
- Ask HN: HNers who got their “Show HNs” on homepage, how is your site doing now? | Hacker News –
- Ask HN: If you were a coder who successfully changed careers, what do you do now? | Hacker News –
These are my links for July 18th through July 19th:
- Dice-O-Matic hopper and elevator – GamesByEmail –
- Troops, Trolls and Troublemakers: A Global Inventory of Organized Social Media Manipulation | The Computational Propaganda Project –
- The limitations of deep learning – The limitations of deep learning
Mon 17 July 2017
By Francois Chollet
This post is adapted from Section 2 of Chapter 9 of my book, Deep Learning with Python (Manning Publications). It is part of a series of two posts on the current limitations of deep learning, and its future.
This post is targeted at people who already have significant experience with deep learning (e.g. people who have read chapters 1 through 8 of the book). We assume a lot of pre-existing knowledge.
Deep learning: the geometric view
The most surprising thing about deep learning is how simple it is. Ten years ago, no one expected that we would achieve such amazing results on machine perception problems by using simple parametric models trained with gradient descent. Now, it turns out that all you need is sufficiently large parametric models trained with gradient descent on sufficiently many examples. As Feynman once said about the universe, "It's not complicated, it's just a lot of it".
- Inside the surprisingly dark world of Rube Goldberg machines | The Verge –
- How to make a friend fast | Hacker News –
- H.264 is magic. : programming –
- Homepage – TheNNTTheNNT –
- Hacker’s guide to Neural Networks (2012) | Hacker News –
- Show HN: 100 Python books, categorized and ranked | Hacker News –
- Why Can’t Americans Get a Raise? | Hacker News –
- “Things I wish” in Hacker News | Hacker News –
- Ask HN: What tasks do you automate? | Hacker News –
- Benchmarking TensorFlow on Cloud CPUs: Cheaper Deep Learning Than Cloud GPUs | Hacker News –
- etienneaudet/Scheduler: Automates completion and emailing of .xlsx time sheet. –
- Understanding Support Vector Machine via Examples | Sadanand’s Notes – In the previous post on Support Vector Machines (SVM), we looked at the mathematical details of the algorithm. In this post, I will be discussing the practical implementations of SVM for classification as well as regression. I will be using the iris dataset as an example for the classification problem, and a randomly generated data as an example for the regression problem.
These are my links for July 5th through July 6th:
- Ask HN: What habits make a programmer great? | Hacker News –
- Learning Elixir: My side-project – code & coffee –
- Running feature specs with Capybara and Chrome headless | Hacker News –