歡迎使用CSDN-markdown編輯器

原創 DoctorSRn 2018-09-03 02:54

隨筆之讀《neural networks and deep learning》

《neural networks and deep learning》是deep learning的入門書之一，鏈接http://neuralnetworksanddeeplearning.com/index.html。
在第一章看到一個很好玩的地方，關於高維空間的一個笑話：

An engineer, a physicist, and a mathematician are discussing how to visualise four dimensions:
Engineer: I never really get it
Physicist: Oh it’s really easy, just imagine three dimensional space over a time- that adds your fourth dimension.
Mathematician: No, it’s way easier than that; just imagine Rn then set n equal to 4.

原鏈接：https://mathoverflow.net/questions/25983/intuitive-crutches-for-higher-dimensional-thinking

發表評論
所有評論
還沒有人評論，想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章

[Fri 19 Jun 2015 ~ Thu 25 Jun 2015] Deep Learning in arxiv

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses Leverage Financial News to Pr

sunbaigui 2020-07-06 23:05:10

Deep Learning：正則化（十）

Sparse Representations Weight decay acts by placing a penalty directly on the model parameters. Another strategy is

蚊子爱牛牛 2020-06-25 22:34:02

Deep Learning：正則化（十三）

Adversarial Training In order to probe the level of understanding a network has of the underlying task, we can sear

蚊子爱牛牛 2020-06-25 22:34:02

Deep Learning：Optimization for Training Deep Models(零)

Of all of the many optimization problems involved in deep learning, the most difficult is neural network training.

蚊子爱牛牛 2020-06-25 22:34:02

Deep Learning：正則化（九）

Parameter Tying and Parameter Sharing Thus far, in this chapter, when we have discussed adding constraints or penal

蚊子爱牛牛 2020-06-25 22:34:02

Deep Learning：正則化（十四）

Tangent Distance, Tangent Prop, and Manifold Tangent Classifier Many machine learning algorithms aim to overcome th

蚊子爱牛牛 2020-06-25 22:34:02

Deep Learning：Optimization for Training Deep Models(一)

How Learning Differs from Pure Optimization Optimization algorithms used for training of deep models differ from tr

蚊子爱牛牛 2020-06-25 22:34:02

Deep Learning：Optimization for Training Deep Models（二）

Challenges in Neural Network Optimization When training neural networks, we must confront the general non-convex ca

蚊子爱牛牛 2020-06-25 22:34:02

人臉關鍵點：TCNN-Tweaked Convolutional Neural Networks

TCNN，全名Tweaked Convolutional Neural Networks， 其中，Tweaking implies fine-tuning the final layers for particular head

TensorSense 2020-06-23 22:21:05

模型壓縮：Networks Slimming-Learning Efficient Convolutional Networks through Network Slimming

Network Slimming-Learning Efficient Convolutional Networks through Network Slimming（Paper） 2017年ICCV的一篇paper，思路清晰，

TensorSense 2020-06-23 22:21:05

人臉關鍵點：MTCNN-Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks

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

TensorSense 2020-06-23 22:20:52

解讀CUDA C Programming Guide (1/5)

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

panda爱学习 2020-06-21 22:34:29

caffe 顯示各類 accuracy(含 accuracy_layer 源碼修改)

caffe 顯示各類 accuracy(含 accuracy_layer 源碼修改) Tags： Deep_Learning 本文主要包含如下內容： caffe 顯示各類 accuracy含 accuracy_layer 源

ProYH 2020-06-21 13:27:22

TF-day1 MINIST識別數字

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

潘小榭 2020-06-21 03:53:38

TF-day6 CNN簡單分類

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

潘小榭 2020-06-21 02:52:04