“Hiring a Machine Learning engineer or Data Scientist in Silicon Valley is becoming like hiring a professional athlete. That’s how demanding it is”?—?The New York Times
基于深度學(xué)習(xí)識(shí)別姑息治療患者
Stanford ML Group 建立了一個(gè)使用深度學(xué)習(xí)算法的程序徐伐，根據(jù)電子健康記錄（Electronic Health Record 耻瑟，EHR，包括病歷、心電圖、醫(yī)療影像等信息）數(shù)據(jù)確定在未來(lái)3-12個(gè)月高風(fēng)險(xiǎn)死亡的住院患者。這些病人的預(yù)警信息將發(fā)送給姑息治療小組，這有助于姑息護(hù)理小組盡早介入、提供服務(wù)商源。
姑息治療（Palliative Care ，在日本谋减、中國(guó)臺(tái)灣翻譯為舒緩醫(yī)學(xué)）起源于 hospice運(yùn)動(dòng)牡彻，最早起源于公元四世紀(jì)。根據(jù)世界衛(wèi)生組織的定義，姑息治療強(qiáng)調(diào)控制疼痛及患者有關(guān)癥狀庄吼，并對(duì)心理缎除、社會(huì)和精神問(wèn)題予以重視，目的是為病人和家屬贏得最好的生活質(zhì)量总寻。
預(yù)測(cè)模型是一個(gè) 18 層的深度神經(jīng)網(wǎng)絡(luò)器罐，輸入?yún)?shù)為一個(gè)病人的 EHR 數(shù)據(jù)，輸出為未來(lái) 3-12 個(gè)月死亡的概率渐行。訓(xùn)練數(shù)據(jù)采用斯坦福醫(yī)院 EHR 數(shù)據(jù)庫(kù)中的歷史數(shù)據(jù)轰坊，包含超過(guò) 200 萬(wàn)名患者的數(shù)據(jù)。EHR 數(shù)據(jù)包括患者過(guò)去 12 個(gè)月的診斷結(jié)論祟印、治療程序肴沫、處方和相關(guān)細(xì)節(jié)（經(jīng)過(guò)脫敏和技術(shù)處理，以替代碼的形式表示）蕴忆，所有數(shù)據(jù)被轉(zhuǎn)換成 13654 維的特征向量颤芬。訓(xùn)練好的模型 AUROC 評(píng)分達(dá)到 0.93 ，交叉驗(yàn)證的平均精度為0.69 分孽文。
對(duì)于機(jī)器學(xué)習(xí)系統(tǒng)來(lái)說(shuō)，使用戶可以根據(jù)預(yù)測(cè)結(jié)果采取行動(dòng)夺艰，需要提供預(yù)測(cè)結(jié)果的詳細(xì)解釋芋哭，這點(diǎn)對(duì)于建立用戶信心至關(guān)重要。Stanford 的程序可以自動(dòng)生成一個(gè)報(bào)告郁副，在病人的 EHR 數(shù)據(jù)中高亮突出對(duì)于預(yù)測(cè)結(jié)果具有重要影響因子的條目减牺。
分類
- 圖像處理 Image Manipulation
- 風(fēng)格轉(zhuǎn)換 Style Transfer
- 圖像分類 Image Classification
- 臉部識(shí)別 Face Recognition
- 視頻穩(wěn)定化 Video Stabilization
- 目標(biāo)檢測(cè) Object Detection
- 自動(dòng)駕駛汽車 Self Driving Car
- 智能推薦 Recommendation Al
- 智能游戲 Gaming Al
- 智能下棋 Chess Al
- 智能醫(yī)學(xué) Medical Al
- 智能演說(shuō) Speech Al
- 智能音樂(lè) Music Al
- 自然語(yǔ)言處理 Natural Language Processing
- 智能預(yù)測(cè) Prediction
Mybridge AI 在 20000 篇關(guān)于創(chuàng)建機(jī)器學(xué)習(xí)應(yīng)用的文章中挑選了前 50 名。從有實(shí)踐經(jīng)驗(yàn)的數(shù)據(jù)科學(xué)家那里學(xué)習(xí)是一個(gè)好方法存谎，我們可以的分享中獲得構(gòu)建拔疚、運(yùn)營(yíng)機(jī)器學(xué)習(xí)應(yīng)用的經(jīng)驗(yàn)教訓(xùn)。50 篇文章大致可以分為 15 個(gè)主題既荚，如下所示：
Recommended Learning
- The Beginner’s Guide to Building an Artificial Intelligence in Unity.
- Deep Learning and Computer Vision A-Z?: Learn OpenCV, SSD & GANs and create image recognition apps.
圖像處理 Image Manipulation
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- Using Deep Learning to Create Professional-Level Photographs
- High Dynamic Range (HDR) Imaging using OpenCV (Python)
風(fēng)格轉(zhuǎn)換 Style Transfer
- Visual Attribute Transfer through Deep Image Analogy
- Deep Photo Style Transfer: A deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style
- Deep Image Prior
圖像分類 Image Classification
- Feature Visualization: How neural networks build up their understanding of images
- An absolute beginner's guide to Image Classification with Neural Networks
- Background removal with deep learning
人臉識(shí)別 Face Recognition
- Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
- Eye blink detection with OpenCV, Python, and dlib
- DEAL WITH IT in Python with Face Detection
視頻穩(wěn)定化 Video Stabilization
目標(biāo)檢測(cè) Object Detection
- How HBO’s Silicon Valley built “Not Hotdog” with mobile TensorFlow, Keras & React Native
- Object detection: an overview in the age of Deep Learning
- How to train your own Object Detector with TensorFlow’s Object Detector API
- Real-time object detection with deep learning and OpenCV
自動(dòng)駕駛汽車 Self Driving Car
- Self-driving Grand Theft Auto V with Python : Intro [Part I] - Sentdex
- Recognizing Traffic Lights With Deep Learning: How I learned deep learning in 10 weeks and won $5,000
智能推薦 Recommendation AI
- Spotify’s Discover Weekly: How machine learning finds your new music
- Artwork Personalization at Netflix
智能游戲 Gaming AI
- MariFlow - Self-Driving Mario Kart w/Recurrent Neural Network
- OpenAI Baselines: DQN. Reproduce reinforcement learning algorithms with performance on par with published results.
- Reinforcement Learning on Dota 2 [Part II]
- Creating an AI DOOM bot
- Phase-Functioned Neural Networks for Character Control
- The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI - Stanford University
- Introducing: Unity Machine Learning Agents – Unity Blog
智能下棋 Chess AI
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- AlphaGo Zero: Learning from scratch | DeepMind
- How Does DeepMind's AlphaGo Zero Work?
- A step-by-step guide to building a simple chess AI
智能醫(yī)學(xué) Medical AI
- CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
- Can you improve lung cancer detection? 2nd place solution for the Data Science Bowl 2017.
- Improving Palliative Care with Deep Learning - Andrew Ng
- Heart Disease Diagnosis with Deep Learning
智能演說(shuō) Speech AI
- Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model - Data Scientists at Google
- Sequence Modeling with CTC
- Deep Voice: Real-time Neural Text-to-Speech - Baidu Silicon Valley AI Lab
- Deep Learning for Siri’s Voice: On-device Deep Mixture Density Networks for Hybrid Unit Selection Synthesis - Apple
智能音樂(lè) Music AI
- Computer evolves to generate baroque music!
- Make your own music with WaveNets: Making a Neural Synthesizer Instrument
自然語(yǔ)言處理 Natural Language Processing
- Learning to communicate: Agents developing their own language - OpenAI Research
- Big Picture Machine Learning: Classifying Text with Neural Networks and TensorFlow
- A novel approach to neural machine translation - Facebook AI Research
- How to make a racist AI without really trying
預(yù)測(cè) Prediction
- Using Machine Learning to Predict Value of Homes On Airbnb
- Engineering Uncertainty Estimation in Neural Networks for Time Series Prediction at Uber
- Using Machine Learning to make parking easier
- How to Predict Stock Prices Easily - Intro to Deep Learning #7
擴(kuò)展閱讀:《The Machine Learning Master》
- Machine Learning(一):基于 TensorFlow 實(shí)現(xiàn)寵物血統(tǒng)智能識(shí)別
- Machine Learning:機(jī)器學(xué)習(xí)項(xiàng)目
- Machine Learning:機(jī)器學(xué)習(xí)算法
- Machine Learning:機(jī)器學(xué)習(xí)書單
- Machine Learning:機(jī)器學(xué)習(xí)參考文集
- Machine Learning:機(jī)器學(xué)習(xí)技術(shù)與知識(shí)產(chǎn)權(quán)法
- Machine Learning:人工智能媒體報(bào)道集
- 數(shù)據(jù)可視化（三）基于 Graphviz 實(shí)現(xiàn)程序化繪圖
