Ideas on interpreting machine learning
Inputs activating different neurons in a neural network. (source: Image courtesy of Patrick Hall and the h2o.ai team, used with permission) You’ve probably heard by now that machine learning algorithms can use big data to predict whether a donor will give to a charity, whether an infant in a NICU will develop sepsis, whether a customer will respond to an ad, and on and on. Machine learning can eve
Optimizing the hyperparameter of which hyperparameter optimizer to use
TL;DR We assess and compare two excellent open-source packages for hyperparameter optimization, Hyperopt and scikit-optimize. Our experiments use XGBoost classifiers on artificial datasets of various sizes, and the associated publicly available code permits a wide range of experiments with different classifiers and datasets. Overall, the experiments show that it is certainly worth using one of the
Bandit Algorithms
The Bayesian approach to learning starts by choosing a prior probability distribution over the unknown parameters of the world. Then, as the learner makes observation, the prior is updated using Bayes rule to form the posterior, which represents the new Continue Reading In an earlier post we analyzed an algorithm called Exp3 for $k$-armed adversarial bandits for which the expected regret is bounde
DeepDive
As of 2017, DeepDive project is in maintenance mode and no longer under active development. The user community remains active, but the original project members can no longer promise exciting new features/improvements or responding to requests. For the more up-to-date research, please see the Snorkel Project or Ce Zhang's Projects. What does DeepDive do? DeepDive is a system to extract value from d
GitHub - thomaskeck/FastBDT: Stochastic Gradient Boosted Decision Trees as Standalone, TMVAPlugin and Python-Interface
FastBDT: A speed-optimized and cache-friendly implementation of stochastic gradient-boosted decision trees for multivariate classification Stochastic gradient-boosted decision trees are widely employed for multivariate classification and regression tasks. This paper presents a speed-optimized and cache-friendly implementation for multivariate classification called FastBDT. FastBDT is one order of
Feature Engineering: Data scientist's Secret Sauce !
It is very tempting for  data science practitioners to opt for the best known  algorithms for a given problem.However It’s not the algorithm alone , which can provide the best solution  ; Model built on carefully engineered and selected features can provide far better results. "Any intelligent fool can make things bigger, more complex, and more violent. It takes a touch of genius -- and a lot of c
Long-term forecasting with machine learning models
Long-term forecasting with machine learning models 03 Aug 2016 Time series analysis has been around for ages. Even though it sometimes does not receive the attention it deserves in the current data science and big data hype, it is one of those problems almost every data scientist will encounter at some point in their career. Time series problems can actually be quite hard to solve, as you deal wit
FGLab: Machine Learning Dashboard
FGLab: Machine Learning Dashboard Future Gadget Laboratory FGLab FGMachine Overview FGLab is a machine learning dashboard, designed to make prototyping experiments easier. Experiment details and results are sent to a database, which allows analytics to be performed after their completion. The server is FGLab, and the clients are FGMachines. After creating projects on FGLab, you write corresponding
GitHub - Yelp/MOE: A global, black box optimization engine for real world metric optimization.
[](https://travis-ci.org/Yelp/MOE) Note: travis link temporarily disabled. The last major MOE commit built successfully but our travis flow appears to be broken (out of date packages perhaps?). Tests and docker still pass/build locally and MOE still works. Metric Optimization Engine. A global, black box optimization engine for real w
Seldon, MLOps for the Enterprise.
Supercharge your deployments with: Production-Ready Inference Servers optimized for popular ML frameworksAdvanced Experimentation and Traffic Splitting including multi-armed bandits, A/B tests, shadows and canariesOptimize Infrastructure Resource Allocation to cost-effectively manage deployed models Gain insights into operational behavior then track, and respond with: Custom Alerts when certain me
GitHub - EpistasisLab/tpot: A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
Master status: Development status: Package information: To try the TPOT2 (alpha) please go here! TPOT stands for Tree-based Pipeline Optimization Tool. Consider TPOT your Data Science Assistant. TPOT is a Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming. TPOT will automate the most tedious part of machine learning by intelligently exploring
一æ©Matrix Factorizationã€äºŒæ©Factorization Machinesã€ä¸‰æ©Field-aware Factorization Machines…『分解ã€ä¸‰æ®µçªãï¼ï¼ã€ - FANCOMI Ad-Tech Blog
ã“ã‚“ã«ã¡ã¯ã€k_oomoriã§ã™ã€‚最近ã€æ©Ÿæ¢°å¦ç¿’ã®åˆ†é‡Žã§Factorization Machines (FM)ã¨ã„ã†æ‰‹æ³•ãŒã‚ã‚‹ã“ã¨ã‚’知りã¾ã—ãŸã€‚Matrix Factorization (MF)ã¯çŸ¥ã£ã¦ã„ãŸã®ã§ã™ãŒã€å…±ã«factorizationã¨ã„ã†å˜èªžã‚’å«ã‚“ã§ã„ã‚‹ãŸã‚ã€ä½•ã‹é–¢ä¿‚ãŒã‚ã‚‹ã®ã ã‚ã†ã‹ï¼Ÿã¨æ°—ã«ãªã‚Šèª¿ã¹ã¦ã¿ã¾ã—ãŸã€‚ ã“ã“ã§ã¯ã‚µãƒ³ãƒ—ルデータã¨ã—ã¦Factorization Machinesã®è«–æ–‡ã§ä½¿ã‚ã‚Œã¦ã„ãŸã‚‚ã®ã‚’使用ã—ã¾ã™ã€‚ タイタニック (TI)ノッティングヒルã®æ‹äºº (NH)スターウォーズ (SW)スタートレック (ST) Alice (A)531 2010-12010-22010-4 Bob (B)45 2009-52009-8 Charlie (C)15 2009-92009-12 表1. æ˜ ç”»ã«å¯¾ã™ã‚‹è©•ä¾¡ Alice, Bob, Charlieã®3人ãŒ4本ã®æ˜ 画作å“ã«å¯¾
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
GitHub - liuruoze/EasyPR: (CGCSTCD'2017) An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations. CGCSTCD = China Graduate Contest on Smart-city Technology and Creative Design
Machine Learning : Pre-processing features | Field of Data Science
GitHub - ceres-solver/ceres-solver: A large scale non-linear optimization library
GitHub - marcotcr/lime: Lime: Explaining the predictions of any machine learning classifier
GitHub - baidu/fast_rgf: Multi-core implementation of Regularized Greedy Forest
http://secml.cs.berkeley.edu/detection_platform/
GitHub - ibayer/fastFM: fastFM: A Library for Factorization Machines
The Fido Project
{{#tags}}- {{label}}
{{/tags}}