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
In Essays.
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".
These are my links for July 14th through July 15th:
- Read Intermediate Python | Leanpub – This book is intended as a concise intermediate level treatise on the Python programming language. There is a need for this due to the lack of availability of materials for python programmers at this level. The material contained in this book is targeted at the programmer that has been through a beginner level introduction to the Python programming language or that has some experience in a different object oriented programming language such as Java and wants to gain a more in-depth understanding of the Python programming language in a holistic manner. It is not intended as an introductory tutorial for beginners although programmers with some experience in other languages may find the very short tutorial included instructive.
The book covers only a handful of topics but tries to provide a holistic and in-depth coverage of these topics. It starts with a short tutorial introduction to get the reader up to speed with the basics of Python; experienced programmers from other object oriented languages such as Java may find that this is all the introduction to Python that they need. This is followed by a discussion of the Python object model then it moves on to discussing object oriented programming in Python. With a firm understanding of the Python object model, it goes ahead to discuss functions and functional programming. This is followed by a discussion of meta-progr
- Code/ Automated & Productive development –
- Review: Days of Wonder’s hot new board game, Yamataï | Ars Technica – Yamataï
- Quilt is a data package manager –
- The Internet of Things – A Disaster – gekk –