- Reinforcement Learning with TensorFlow
- Sayon Dutta
- 99字
- 2021-08-27 18:51:52
Notation
Let the data be of the form , where:
,
(number of classes = 2 because it's a binary classification)
is 'n' dimensional, that is,
(refers to the preceding diagram)
The number of training examples is m. Thus the training set looks as follows:
.
m = size of training dataset.
And, since
, where, each
.
Therefore,
is a matrix of size n * m, that is, number of features * number of training examples.
, a vector of m outputs, where, each
.
Parameters : Weights
, and bias
,
where
and
is a scalar value.
推薦閱讀
- Hands-On Deep Learning with Apache Spark
- Spark編程基礎(Scala版)
- Blockchain Quick Start Guide
- Mastering Elastic Stack
- 數據庫原理與應用技術
- OpenStack Cloud Computing Cookbook(Second Edition)
- Cloudera Administration Handbook
- Apache Superset Quick Start Guide
- 大學C/C++語言程序設計基礎
- 大數據驅動的設備健康預測及維護決策優化
- 基于Xilinx ISE的FPAG/CPLD設計與應用
- Hands-On Data Warehousing with Azure Data Factory
- MATLAB-Simulink系統仿真超級學習手冊
- JRuby語言實戰技術
- 智能制造系統及關鍵使能技術