iT邦幫忙

鐵人檔案

第 11 屆 iThome 鐵人賽
回列表
Google Developers Machine Learning

ML Study Jam Journey 系列

透過 Google Developers 推出的 ML Study Jam 活動學習 Machine Learning 基礎知識。

鐵人鍊成 | 共 30 篇文章 | 2 人訂閱 訂閱系列文 RSS系列文
DAY 21

Day 21 Art and Science of Machine Learning (cont.)

Logistic Regression Use Cross Entropy typically Two problems Weights will b...

2019-10-05 ‧ 由 kehsyu 分享
DAY 22

Day 22 Art and Science of Machine Learning (cont.)

Neural Networks Linear Model can be represented as nodes and edgesNon-Linear Tra...

2019-10-06 ‧ 由 kehsyu 分享
DAY 23

Day 23 Art and Science of Machine Learning (cont.)

Logistic Regression Use Cross Entropy typically Two problems Weights will b...

2019-10-07 ‧ 由 kehsyu 分享
DAY 24

Day 24 Art and Science of Machine Learning (cont.)

ML models Parameters - Change during training Hyper-parameters - Set before tra...

2019-10-08 ‧ 由 kehsyu 分享
DAY 25

Day 25 Art and Science of Machine Learning (cont.)

Easier to train a model with d inputs than a model with N inputsEmbeddings can b...

2019-10-09 ‧ 由 kehsyu 分享
DAY 26

Day 26 Art and Science of Machine Learning (cont.)

Multi-class problems one vs all one vs one Use one softmax loss for all possi...

2019-10-10 ‧ 由 kehsyu 分享
DAY 27

Day 27 Art and Science of Machine Learning (cont.)

Custom Estimator Modeling Checkpointing Memory size Training, evaluating Adjust...

2019-10-11 ‧ 由 kehsyu 分享
DAY 28

Day 28 Summary

Introduction Train an ML model with examples (Training) label - true answer mod...

2019-10-12 ‧ 由 kehsyu 分享
DAY 29

Day 29 Summary (cont.)

Intro to TensorFlow Cloud Machine Learning Engine Train, deploy, and production...

2019-10-13 ‧ 由 kehsyu 分享
DAY 30

Day 30 Summary (cont.)

Art and Science of Machine Learning Neural Networks Linear Model can be represe...

2019-10-14 ‧ 由 kehsyu 分享