W!o+ 的《小伶鼬工坊演義》︰神經網絡【百家言】一

新唐書/卷176
韓愈

韓愈,字退之,鄧州南陽人。七世祖茂,有功於後魏,封安定王。父仲卿,為武昌令,有美政,既去,縣人刻石頌德。終秘書郎。愈生三歲而孤,隨伯兄會貶官嶺表。會卒,嫂鄭鞠之。愈自知讀書,日記數千百言,比長,盡能通《六經》、百家學。擢進士第。會董晉為宣武節度使,表署觀察推官。晉卒,愈從喪出,不四日,汴軍亂,乃去。依武甯節度使張建封,建封辟府推官。操行堅正,鯁言無所忌。調四門博士,遷監察禦史。上疏極論宮市,德宗怒,貶陽山令。有愛在民,民生子多以其姓字之。改江陵法曹參軍。元和初 ,權知國子博士,分司東都,三歲為真。改都官員外郎,即拜河南令。遷職方員外郎。

……

每言文章自漢司馬相如、太史公、劉向、揚雄後,作者不世出,故愈深探本元,卓然樹立,成一家言。其《原道》、《原性》、《師說》等數十篇,皆奧衍閎深,與孟軻、揚雄相表裏而佐佑《六經》雲。至它文,造端置辭,要為不襲蹈前人者。然惟愈為之,沛然若有餘,至其徒李翱、李漢、皇甫湜從而效之,遽不及遠甚。從愈游者,若孟郊、張籍,亦皆自名於時。

───

 

欲成一家言者,須先讀百家書。深思熟慮方能去蕪存菁,正反論難方可明辨要點。或此正是 Michael Nielsen 先生之所以宣講︰

Other techniques

Each technique developed in this chapter is valuable to know in its own right, but that’s not the only reason I’ve explained them. The larger point is to familiarize you with some of the problems which can occur in neural networks, and with a style of analysis which can help overcome those problems. In a sense, we’ve been learning how to think about neural nets. Over the remainder of this chapter I briefly sketch a handful of other techniques. These sketches are less in-depth than the earlier discussions, but should convey some feeling for the diversity of techniques available for use in neural networks.

───

 

【輔翼資料】

Awesome Deep Learning Awesome

Table of Contents

Free Online Books

  1. Deep Learning by Yoshua Bengio, Ian Goodfellow and Aaron Courville (05/07/2015)
  2. Neural Networks and Deep Learning by Michael Nielsen (Dec 2014)
  3. Deep Learning by Microsoft Research (2013)
  4. Deep Learning Tutorial by LISA lab, University of Montreal (Jan 6 2015)
  5. neuraltalk by Andrej Karpathy : numpy-based RNN/LSTM implementation
  6. An introduction to genetic algorithms
  7. Artificial Intelligence: A Modern Approach
  8. Deep Learning in Neural Networks: An Overview

Courses

  1. Machine Learning – Stanford by Andrew Ng in Coursera (2010-2014)
  2. Machine Learning – Caltech by Yaser Abu-Mostafa (2012-2014)
  3. Machine Learning – Carnegie Mellon by Tom Mitchell (Spring 2011)
  4. Neural Networks for Machine Learning by Geoffrey Hinton in Coursera (2012)
  5. Neural networks class by Hugo Larochelle from Université de Sherbrooke (2013)
  6. Deep Learning Course by CILVR lab @ NYU (2014)
  7. A.I – Berkeley by Dan Klein and Pieter Abbeel (2013)
  8. A.I – MIT by Patrick Henry Winston (2010)
  9. Vision and learning – computers and brains by Shimon Ullman, Tomaso Poggio, Ethan Meyers @ MIT (2013)
  10. Convolutional Neural Networks for Visual Recognition – Stanford by Fei-Fei Li, Andrej Karpathy (2015)
  11. Convolutional Neural Networks for Visual Recognition – Stanford by Fei-Fei Li, Andrej Karpathy (2016)
  12. Deep Learning for Natural Language Processing – Stanford
  13. Neural Networks – usherbrooke
  14. Machine Learning – Oxford (2014-2015)
  15. Deep Learning – Nvidia (2015)
  16. Graduate Summer School: Deep Learning, Feature Learning by Geoffrey Hinton, Yoshua Bengio, Yann LeCun, Andrew Ng, Nando de Freitas and several others @ IPAM, UCLA (2012)
  17. Deep Learning – Udacity/Google by Vincent Vanhoucke and Arpan Chakraborty (2016)
  18. Deep Learning – UWaterloo by Prof. Ali Ghodsi at University of Waterloo (2015)

………