鐵人檔案
透過 Google Developers 推出的 ML Study Jam 活動學習 Machine Learning 基礎知識。
Logistic Regression Use Cross Entropy typically Two problems Weights will b...
Neural Networks Linear Model can be represented as nodes and edgesNon-Linear Tra...
Logistic Regression Use Cross Entropy typically Two problems Weights will b...
ML models Parameters - Change during training Hyper-parameters - Set before tra...
Easier to train a model with d inputs than a model with N inputsEmbeddings can b...
Multi-class problems one vs all one vs one Use one softmax loss for all possi...
Custom Estimator Modeling Checkpointing Memory size Training, evaluating Adjust...
Introduction Train an ML model with examples (Training) label - true answer mod...
Intro to TensorFlow Cloud Machine Learning Engine Train, deploy, and production...
Art and Science of Machine Learning Neural Networks Linear Model can be represe...
