Converting categorical data into numbers with Pandas and Scikit-learn - FastML
Many machine learning tools will only accept numbers as input. This may be a problem if you want to use such tool but your data includes categorical features. To represent them as numbers typically one converts each categorical feature using “one-hot encoding”, that is from a value like “BMW” or “Mercedes” to a vector of zeros and one 1. This functionality is available in some software libraries.
Deep learning architecture diagrams - FastML
As a wild stream after a wet season in African savanna diverges into many smaller streams forming lakes and puddles, so deep learning has diverged into a myriad of specialized architectures. Each architecture has a diagram. Here are some of them. Neural networks are conceptually simple, and that’s their beauty. A bunch of homogenous, uniform units, arranged in layers, weighted connections between
What is better: gradient-boosted trees, or a random forest? - FastML
Folks know that gradient-boosted trees generally perform better than a random forest, although there is a price for that: GBT have a few hyperparams to tune, while random forest is practically tuning-free. Let’s look at what the literature says about how these two methods compare. Supervised learning in 2005 In 2005, Caruana et al. made an empirical comparison of supervised learning algorithms [vi
What you wanted to know about TensorFlow - FastML
TensorFlow is a new deep learning library from Google. Immediately after release it became the most starred deep learning package on GitHub. From the hype one could conclude that TensorFlow is the best thing since sliced bread. Is it? TensorFlow vs Theano The first thing to realize about TensorFlow is that it’s a low-level library, meaning you’ll be multiplying matrices and vectors. Tensors, if yo
Deep nets generating stuff - FastML
The last few weeks have been a time of neural nets generating stuff. By deep nets we mean recurrent and convolutional neural networks, while the stuff is text, music, images and even video. Text and music It all started with Andrej Karpathy’s blog post on recurrent neural networks generating text, character by character. This is by no means a new idea - it goes back to 2011 paper by Sutskever, Mar
What you wanted to know about AI - FastML
Recently a number of famous people, including Bill Gates, Stephen Hawking and Elon Musk, warned everybody about the dangers of machine intelligence. You know, SkyNet. Terminators. The Matrix. HAL 9000. (Her would be OK probably, we haven’t seen that movie.) Better check that AI, then, maybe it’s the last moment to keep it at bay. State of the AIt Real stupidity beats artificial intelligence every
Torch vs Theano - FastML
Recently we took a look at Torch 7 and found its data ingestion facilities less than impressive. Torch’s biggest competitor seems to be Theano, a popular deep-learning framework for Python. These two have been having “who is faster” competition going for a few years now. It’s been documented in the following papers: J. Bergstra, O. Breuleux, F. Bastien, P. Lamblin, R. Pascanu, G. Desjardins, J. Tu
Geoff Hinton's Dark Knowledge - FastML
Geoff Hinton had been silent since he went to work for Google. Recently, however, Geoff has come out and started talking about something he calls dark knowledge. Maybe some questions shouldn’t be asked, but what does he mean by that? Image credit: Shadow of the Vampire Perhaps the first thing to understand here is the problem being solved: model complexity at test time. Complex models like ensembl
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
