I have been working on Machine learning algorithms (SVM) and some clustering algorithms (k-means, random forest, HMM etc) for quite some time. I use these algorithms for data classification (this data is of complex form).

Recently, I came across neural networks and I was suggested that NN and ANN could be used to do the same.

Are there any specific requirements to start working with NN? As I am completely new to it, are there any tutorials which can help me get some basic idea about NN and ANN?


Why to use Neural Networks:

They are useful for implementing complex non-linear functions in regression, classification and other methods. Due to technological advances in the past years and decades computers can store and manager larger and larger datasets and compute much more rapidly. Therefore you can use more complex models like Neural Networks.


As tutorials I recommend Week 4 and 5 of Andrew Ngs Machine Learning course and this coursera course by Geoffrey Hinton who is an expert for Neural Networks. You can also start learning by coding with deep learning frameworks. As far as I know Tensorflow is the leading now in industry, but also other deep learning frameworks like Theano offer an opportunity to implement state of the art research.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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