- 【代码】Pyreclab: Recommendation lab for Python
Pyreclab is a recommendation library designed for training recommendation models with a friendly and easy-to-use interface, keeping a good performance in memory and CPU usage.
In order to achieve this, Pyreclab is built as a Python module to give a friendly access to its algorithms and it is completely developed in C++ to avoid the lack of performace of the interpreted languages.
2.【博客】Optimisation and training techniques for deep learning
Today we’re looking at the ‘optimisation and training techniques’ section from the ‘top 100 awesome deep learning papers’ list.
- Random search for hyper-parameter optimization, Bergstra & Bengio 2012
- Improving neural networks by preventing co-adaptation of feature detectors, Hinton et al., 2012
- Dropout: a simple way to prevent neural networks from overfitting, Srivastava et al., 2014
- Adam: a method for stochastic optimization, Kingma & Ba, 2015
- Batch normalization: accelerating deep network training by reducing internal covariate shift, Ioffy & Szegedy, 2015
- Delving deep into rectifiers: surpassing human-level performance on ImageNet classification, He et al., 2015
3.【博客】The Lisp approach to AI (Part 1)
If you are a programmer that reads about the history and random facts of this lovely craft, and practice it ad honorem — just for fun — , you have found yourself reading about a programming language called Lisp. Some praise it as a software miracle, as the best tool for programming. Some even dare to call Lisp one of the best programming languages ever invented (even if that doesn’t make sense at all). After all, before Python, Scala, Haskell, there was programming, and before Deep Learning there was Artificial Intelligence.
4.【代码】Fasttext：Pre-trained word vectors
We are publishing pre-trained word vectors for 90 languages, trained on Wikipedia. These are vectors in dimension 300, trained with the default parameters of fastText.
5.【项目】Self-driving cars in the browser
This is a project I have been working on for quite some time now. These cars learned how to drive by themselves. They got feedback on what good and what bad actions are based on their current speed as a form of reward. Powered by a neural network.
You can drag the mouse to draw obstacles, which the cars must avoid. Play around with this demo and get excited about machine learning!
The following is a more detailed description of how this works. You may stop reading here and just play with the demo if you're not interested in the technical background!