1. 聊聊信息熵 2. 決策樹是何許人也 3. 信息增益、增益率、基尼係數 4. 隨機森林 (三個臭皮匠頂個諸葛亮) 5. AdaBoost 竟如此簡單 6. XGBoost, 機器學習的大殺器
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses Leverage Financial News to Pr
Sparse Representations Weight decay acts by placing a penalty directly on the model parameters. Another strategy is
Adversarial Training In order to probe the level of understanding a network has of the underlying task, we can sear
Of all of the many optimization problems involved in deep learning, the most difficult is neural network training.
Parameter Tying and Parameter Sharing Thus far, in this chapter, when we have discussed adding constraints or penal
Tangent Distance, Tangent Prop, and Manifold Tangent Classifier Many machine learning algorithms aim to overcome th
How Learning Differs from Pure Optimization Optimization algorithms used for training of deep models differ from tr
Challenges in Neural Network Optimization When training neural networks, we must confront the general non-convex ca
TCNN，全名Tweaked Convolutional Neural Networks， 其中，Tweaking implies fine-tuning the final layers for particular head
Network Slimming-Learning Efficient Convolutional Networks through Network Slimming（Paper） 2017年ICCV的一篇paper，思路清晰，
創新點： 1. 首次將級聯和多任務結合起來，之前有單純級聯的DCNN，單純多任務的TCDCN 2. 提出 a new online hard sample mining strategy，沒接觸過hard sample min
本系列爲《解讀CUDA C Programming Guide》. https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#axzz4FIp5fBgM 本書旨在介紹
當我們開始學習編程的時候，第一件事往往是學習打印”Hello World”。就好比編程入門有Hello World，機器學習入門有MNIST 主要步驟 - 獲取數據 - 建立模型 - 定義 tensor，variabl
主要內容： 何爲CNN code 一、何爲CNN 圖解何爲CNN http://www.jianshu.com/p/6daa1af1cf37 深入理解： http://study.163.com/course/cours
一.深度卷積神經網絡學習筆記（一）： 1.這篇文章以賈清揚的ppt說明了卷積的實質，更說明了卷積輸出圖像大小應該爲： 假設輸入圖像尺寸爲W，卷積核尺寸爲F，步幅（stride）爲S（卷積核移動的步幅），Padding使用P（用於
