オーソドックス な アプローチ（一般的手法） まず は、以下 が よくまとまっている。 株式会社クロスコンパス・インテリジェンス（2016.10.5）「NVIDIA GPU TECHNOLOGY CONFERENCE JAPAN 2016 Industry Deep Learning」 異常値予測 を 行う アプローチ としては、以下 が 一般的な考え方 の ようだ。 （データ量の多い）正常時のデータ挙動の特徴パターンを学ばせて、 新規データが上記の特徴パターンから乖離している場合を、異常とみなす 上記のアプローチをとる理由 は、「異常発生時のデータ」の取得可能件数 は、「正常時のデータ」 に 比べて、取得できるデータの件数 が 圧倒的に少ない から である。 上記のスライド で 挙げられている AutoEncoderモデル や LSTMモデル を 採用し、 AutoEncoderモデル

Data / MLEngineering Uncertainty Estimation in Neural Networks for Time Series Prediction at UberSeptember 6, 2017 / Global Accurate time series forecasting during high variance segments (e.g., holidays and sporting events) is critical for anomaly detection, resource allocation, budget planning, and other related tasks necessary to facilitate optimal Uber user experiences at scale. Forecasting the

Deep Learning for NLP Best Practices Neural networks are widely used in NLP, but many details such as task or domain-specific considerations are left to the practitioner. This post collects best practices that are relevant for most tasks in NLP. This post gives an overview of best practices relevant for most tasks in natural language processing. Update July 26, 2017: For additional context, the Ha

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

Understanding the backward pass through Batch Normalization Layer At the moment there is a wonderful course running at Standford University, called CS231n - Convolutional Neural Networks for Visual Recognition, held by Andrej Karpathy, Justin Johnson and Fei-Fei Li. Fortunately all the course material is provided for free and all the lectures are recorded and uploaded on Youtube. This class gives

Summary This document describes my part of the 2nd prize solution to the Data Science Bowl 2017 hosted by Kaggle.com. I teamed up with Daniel Hammack. His part of the solution is decribed here The goal of the challenge was to predict the development of lung cancer in a patient given a set of CT images. Detailed descriptions of the challenge can be found on the Kaggle competition page and this blog

Predicting lung cancer The Data Science Bowl is an annual data science competition hosted by Kaggle. In this year’s edition the goal was to detect lung cancer based on CT scans of the chest from people diagnosed with cancer within a year. To tackle this challenge, we formed a mixed team of machine learning savvy people of which none had specific knowledge about medical image analysis or cancer pre

The receptive field is perhaps one of the most important concepts in Convolutional Neural Networks (CNNs) that deserves more attention from the literature. All of the state-of-the-art object recognition methods design their model architectures around this idea. However, to my best knowledge, currently there is no complete guide on how to calculate and visualize the receptive field information of a

Lecture 1 introduces the concept of Natural Language Processing (NLP) and the problems NLP faces today. The concept of representing words as numeric vectors is then introduced, and popular approaches to designing word vectors are discussed. Key phrases: Natural Language Processing. Word Vectors. Singular Value Decomposition. Skip-gram. Continuous Bag of Words (CBOW). Negative Sampling. Hierarchi

The first three blog posts in my “Deep Learning Paper Implementations” series will cover Spatial Transformer Networks introduced by Max Jaderberg, Karen Simonyan, Andrew Zisserman and Koray Kavukcuoglu of Google Deepmind in 2016. The Spatial Transformer Network is a learnable module aimed at increasing the spatial invariance of Convolutional Neural Networks in a computationally and parameter effic

This is the original Theano implementation of the algorithm of the paper "Session-based Recommendations With Recurrent Neural Networks", with the extensions introduced in the paper "Recurrent Neural Networks with Top-k Gains for Session-based Recommendations". Make sure to always use the latest version as baseline and cite both papers when you do so! The code was optimized for fast execution on th

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert