43
$\begingroup$

I want to learn Neural Networks. I am a Computational Linguist. I know statistical machine learning approaches and can code in Python.

I am looking to start with its concepts, and know one or two popular models which may be useful from a Computational Linguistics perspective.

I browsed the web for reference and found a few books and materials.

  • Ripley, Brian D. (1996) Pattern Recognition and Neural Networks, Cambridge

  • Bishop, C.M. (1995) Neural Networks for Pattern Recognition, Oxford: Oxford University Press.

  • some links, like this thesis, these course notes (University of Toronto Psychology Department), these course notes (University of Wisconsin Computer Science) and this slideshow (Facebook Research).

Coursera courses are generally nice, if anyone knows anything relevant from them. I prefer materials with lucid language and ample examples.

Improve this question
$\endgroup$
4
  • 2
    $\begingroup$ I have tried to edit the text to make it more reasonable, feel free to amend my edits if you feel that they have changed anything in a way you do not like. $\endgroup$
    – Silverfish
    Commented Aug 2, 2016 at 17:03
  • $\begingroup$ It's not apparent what you are asking. Please make explicit what you hope to learn from CV respondents. $\endgroup$
    – user78229
    Commented Aug 2, 2016 at 19:48
  • $\begingroup$ youtube.com/channel/UC0z_jCi0XWqI8awUuQRFnyw highly recommend this Oxford university's professor course $\endgroup$
    – Joe Half Face
    Commented Aug 2, 2016 at 21:44
  • $\begingroup$ My initial objective is to learn the fundamentals of ANN and master one or two models to create some text mining tools, like PoS Tagging or Sentiment Analysis. Once I get slight depth I believe I may move on my own. $\endgroup$
    – HIGGINS
    Commented Aug 3, 2016 at 7:36

5 Answers 5

Reset to default
34
$\begingroup$

You're in luck! There are an amazing number of resources available at the moment. In particular, you could look at:

  • a Coursera course starting soon
  • a recently published online textbook by some of the leaders in the field (Goodfellow, Bengio and Courville)
  • these lecture notes, and this overview, which are more oriented towards natural language processing
  • a set of blog posts with beautiful visualizations by Chris Olah
  • two well-supported toolkits with python interfaces and online tutorials: Tensorflow and Theano
Improve this answer
$\endgroup$
3
  • $\begingroup$ Start with a recursive neural net wildml.com/2015/09/… $\endgroup$
    – user3916597
    Commented Aug 3, 2016 at 20:16
  • $\begingroup$ Read up on how it works. Then progress to non-recursive nets and back propogation finding code for each. $\endgroup$
    – user3916597
    Commented Aug 3, 2016 at 20:16
  • 2
    $\begingroup$ Can you provide authors and titles for everything that you are citing, so that your answer becomes searchable and remains useful even if some of the links go dead? $\endgroup$
    – amoeba
    Commented Aug 4, 2016 at 13:50
17
$\begingroup$

Main references:

Courses on deep learning:

NLP-oriented:

Vision-oriented:

Toolkit-specific tutorials:

Improve this answer
$\endgroup$
0
6
$\begingroup$

http://www.kdnuggets.com/2015/11/seven-steps-machine-learning-python.html

http://neuralnetworksanddeeplearning.com/

This has been my favorite resources. Started with the Stanford machine learning course, but prefer reading over lectures. Especially because the readings are example-based.

Improve this answer
$\endgroup$
3
  • 2
    $\begingroup$ Welcome to the site. At present this is more of a comment than an answer. You could expand it, perhaps by giving a summary of the information at the link, or we can convert it into a comment for you. $\endgroup$
    – gung - Reinstate Monica
    Commented Aug 2, 2016 at 17:49
  • 2
    $\begingroup$ This looks potentially like a helpful answer, but it's a little ambiguous: what are these "readings" to which you refer? To which of the two links do your comments apply? $\endgroup$
    – whuber ♦
    Commented Aug 2, 2016 at 18:14
  • $\begingroup$ Thank you all for your kind effort and time. Hope I can respect it by learning well. $\endgroup$
    – HIGGINS
    Commented Aug 2, 2016 at 18:42
3
$\begingroup$

Neural Networks and Deep Learning is an approachable starting-point.

Neural Networks and Deep Learning is a free online book. The book will teach you about:

Neural networks, a beautiful biologically-inspired programming paradigm which enables a computer to learn from observational data Deep learning, a powerful set of techniques for learning in neural networks Neural networks and deep learning currently provide the best solutions to many problems in image recognition, speech recognition, and natural language processing. This book will teach you many of the core concepts behind neural networks and deep learning.

Improve this answer
$\endgroup$
0
$\begingroup$

For fast learning I would choose:

This Deep Learning lecture from the great teacher-researcher Nando de Freitas: https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearning/

For practical programming theory understanding in Python this material from Andrej Karpathy: http://cs231n.github.io/

And for NLP: https://arxiv.org/abs/1510.00726

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.