Why does deep and cheap learning work so well?
We show how the success of deep learning could depend not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can approximate arbitrary functions well, the class of functions of practical interest can frequently be approximated through "cheap learning" with exponentially fewer parameters than generic ones. We explore how properties freq
Benchmarks | TensorFlow
Deploy ML on mobile, microcontrollers and other edge devices
Tuning Your DBMS Automatically with Machine Learning | Amazon Web Services
AWS Machine Learning Blog Tuning Your DBMS Automatically with Machine Learning This is a guest post by Dana Van Aken, Andy Pavlo, and Geoff Gordon of Carnegie Mellon University. This project demonstrates how academic researchers can leverage our AWS Cloud Credits for Research Program to support their scientific breakthroughs. Database management systems (DBMSs) are the most important component of
fastText/pretrained-vectors.md at master · facebookresearch/fastText · GitHub
Pre-trained word vectors We are publishing pre-trained word vectors for 294 languages, trained on Wikipedia using fastText. These vectors in dimension 300 were obtained using the skip-gram model described in Bojanowski et al. (2016) with default parameters. Format The word vectors come in both the binary and text default formats of fastText. In the text format, each line contain a word followed by
8 Reasons Why Analytics / Machine Learning Models Fail To Get Deployed
Introduction Don’t be a data scientist whose models fail to get deployed! An epic example of model deployment failure is from Netflix Prize Competition. In a short story, it was an open competition. Participants had to build a collaborative filtering algorithm to predict user rating for films. The winners received grand prize of US$1,000,000. In the end, the complete model never got deployed. Not
The Amazing Power of Word Vectors - KDNuggets
The Amazing Power of Word Vectors A fantastic overview of several now-classic papers on word2vec, the work of Mikolov et al. at Google on efficient vector representations of words, and what you can do with them. For today’s post, I’ve drawn material not just from one paper, but from five! The subject matter is ‘word2vec’ – the work of Mikolov et al. at Google on efficient vector representations of
A comprehensive beginner's guide to start ML with Amazon Web Services (AWS)
Introduction Learn to connect AWS instance with your laptop / desktop for faster computation! Do you struggle with working on big data (large data sets) on your laptop ? I recently tried working on a 10 GB image recognition data set. But, due to the limited computational power of my laptop, I couldn’t proceed further. I was determined to solve this problem, and thankfully, in few hours, I managed
Adversarial validation, part one - FastML
Many data science competitions suffer from a test set being markedly different from a training set (a violation of the identically distributed assumption). It is then difficult to make a representative validation set. We propose a method for selecting training examples most similar to test examples and using them as a validation set. The core of this idea is training a probabilistic classifier to
How to Explain Machine Learning to a Software Engineer - KDNuggets
How to Explain Machine Learning to a Software Engineer How do you explain what machine learning is to the uninitiated software engineer? Read on for one perspective on doing so. Software engineering is about developing programs or tools to automate tasks. Instead of "doing things manually," we write programs; a program is basically just a machine-readable set of instructions that can be executed b
Building a Production Machine Learning Infrastructure - MachineLearningMastery.com
[New Book] Click to get Mastering Digital Art with Stable Diffusion! Use the offer code 20offearlybird to get 20% off. Hurry, sale ends soon! Midwest.io is was a conference in Kansas City on July 14-15 2014. At the conference, Josh Wills gave a talk on what it takes to build production machine learning infrastructure in a talk titled “From the lab to the factory: Building a Production Machine Lear
Redirecting…
Redirecting… Click here if you are not redirected.
機械学習の分類の話を損失関数と決定境界を中心に整理してみた - once upon a time,
機械学習の分類の話を、主に決定境界と損失関数の観点から整理してみました。 とはいっても、k-NNとか損失関数関係ないのもいます。 最初ははてなブログに書こうとしたのですが、数式を埋め込むのが辛かったのでjupyter notebookにしました。 github.com [追記] githubだと日本語を含む数式のレンダーが壊れるので、nbviewerの方がいいかもしれません。 https://nbviewer.jupyter.org/github/chezou/notebooks/blob/master/classification.ipynb [/追記] パーセプトロンが見直されたのはなんでだっけ、SVMってどういう位置づけだっけ、というのを確認できればなぁと思っています。 多層パーセプトロンまでに至るところの流れがうまく伝わればなぁと思っています。 間違いなどがあれば、是非ご指摘いただ
Number plate recognition with Tensorflow - Matt's Ramblings
Introduction Over the past few weeks I’ve been dabbling with deep learning, in particular convolutional neural networks. One standout paper from recent times is Google’s Multi-digit Number Recognition from Street View. This paper describes a system for extracting house numbers from street view imagery using a single end-to-end neural network. The authors then go on to explain how the same network
Neural Networks in Javascript - webkid blog
Neural networks provide the possibility to solve complicated non linear problems. They can be used in various areas such as signal classification, forecasting timeseries and pattern recognition. A neural network is a model inspired by the human brain and consists of multiple connected neurons. The network consists of a layer of input neurons (where the information goes in), a layer of output neuro
Scala製の機械学習フレームワーク「PredictionIO」 | blue engineer blog
こんにちは、エンジニアの渋江です。 前々からGitHubで気になってStarしてた割に中々触る機会がなかったので機械学習の勉強用として触ってみました。 PredictionIOとは Spark上で動作するScala製のオープンソース機械学習フレームワークです。 以下のようなアプリケーションを作ることができます。 ・アイテムのレコメンド（例えば、映画、製品、食品） ・ユーザーの行動を予測 ・アイテムの類似性を識別 ・アイテムのランキング 公式リポジトリ：https://github.com/PredictionIO/PredictionIO/ 今回はレコメンデーションができる様になるまで公式ドキュメント(英語)を見ながら進めていきます。 前提としてMac上での操作になります。 PredictionIOのインストール 対話式でインストールしていきます。 $ bash -c "$(
Gradient Boosting Decision Treeでの特徴選択 in R | 分析のおはなし。
Gradient Boosting Decision Tree(GBDT)を勉強したので、その概要とRでのパッケージの簡単な使い方を乗っけておきます。 1. そもそもGBDTってなんだよっていう話。 単純に言えば、複数の決定木を作成して、集団で学習させる方法の事です。 １本決定木を作り、上手くモデルで説明が出来なかったobservationに対して重みを付け、重みのついた状態で次の木を作り、また重みを付けて・・・ というステップを指定した本数分だけ繰り返します。 誤差に対して学習しなおしてくれるので、決定木よりもっと良いモデルが出来上がります。 理論の詳細はこちらの本を参考にしていただければと。 英語版は著者サイトで無料公開されています。英語大丈夫な人はこちらを参照するとよいかと。 http://statweb.stanford.edu/~tibs/ElemStatLearn/ あとこのイ
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
http://www.sysml.cc/
SysML 18: Jeff Dean, Systems and Machine Learning Symbiosis
Bagging, boosting and stacking in machine learning
Greedy Feature Selection for Subspace Clustering