發(fā)簡信
IP屬地：西藏
-
辨析matmul product（一般矩陣乘積）失受，hadamard product（哈達瑪積）虑啤、kronecker product（克羅內(nèi)克積）
矩陣乘法 1. matmul product（一般矩陣乘積） m x p矩陣A與p x n矩陣B拂募，那么稱 m x n 矩陣C為矩陣A與矩陣B的一...
-
Conditional Generative Adversarial Nets論文總結(jié)
論文地址：Conditional Generative Adversarial Nets 2014年，Goodfellow提出了Generati...
-
What is the differenc between boost, ensemble, bootstrap and bagging?
Boosting is the idea of training iteratively the same “weak” classifier,...
-
先驗概率帅刊，后驗概率纸泡，likelihood的中文解說
先驗概率，后驗概率赖瞒，likelihood 的中文觀點解說 原因：之前學概論的時候有點沒搞明白為什么要這樣命名這些概率項弟灼， 動機： 現(xiàn)在有很多，m...
-
Resource Data structure and algo
here's some video resource from outside, which you cannot get by googlin...
-
Stacked Denoising and Stacked Convolutional AutoencodersAn Evaluation of Transformation Robustness for Spatial Data Representati...
-
Reinforcement learning (1)（2018-08-23 cont.）
Reason for the series OK this article only serve as my study notes for r...
-
機器學習感知機（統(tǒng)計學習-李航）感知機 概述 感知機是二類分類的線性分類模型冒黑，其輸入為實例的特征向量田绑，輸出為實例的類別，取+1和-1二值抡爹。感知機學習旨在求出將訓練數(shù)據(jù)進行線性劃...