7 Steps for becoming Deep Learning Expert

转载自：

7 Steps for becoming Deep Learning Expert | Ankit Agarwal | 领英
https://www.linkedin.com/pulse/7-steps-becoming-deep-learning-expert-ankit-agarwal
One of the frequent questions we get about our work is - "Where to start learning Deep Learning?” Lot of courses and tutorials are available freely online, but it gets overwhelming for the uninitiated. We have curated a few resources
below which may help you begin your trip down the Deep Learning rabbit hole.

1. The
first step is to understand Machine learning, the best resource for which is Andrew
Ngs (Ex-Google, Stanford, Baidu), an online course at coursera.
Going through the lectures are enough to understand the basics, but assignments take your understanding to another level.

2. Next step is to develop intuition for Neural Networks. So go forth, write your first
Neural Network and play with it.

3. Understanding
Neural networks are important, but simple Neural Networks not sufficient to solve the most interesting problems. A variation - Convolution Neural Networks work really well for visual tasks. Standord lecture notes and slides on the same are here:CS231n
Convolutional Neural Networks for Visual Recognition(notes),
and CS231n:
Convolutional Neural Networks for Visual Recognition (lecture
slides). Also here and here are
two great videos on CNNs.



4. Next
step is to get following for running your first CNN on your own PC.

Buy GPU and
install CUDA 

Install Caffe and its
GUI wrapper Digit 

Install Boinc (This
will not help you in Deep Learning, but would let other researchers use your GPU in its idle time, for Science) 

5. Digit
provides few algorithms such as - Lenet for
character recognition and Googlenet for
image classification algorithms. You need to download dataset
for Lenet and dataset
for Googlenet  to run these algorithms.
You may modify the algorithms and try other fun visual image recognition tasks, like we did here.

6. For
various Natural Language Processing (NLP) tasks, RNNs (Recurrent Neural Networks) are really the best. The best place to learn about RNNs is the Stanford
lecture videos here. You can
download Tensorflow and
use it for building RNNs.

7. Now
go ahead and choose a Deep Learning problem ranging from facial detection to speech recognition to a self-driving car, and solve it.

If you are through with all the above steps - Congratulations! Go ahead and apply for a position at Google, Baidu, Microsoft, Facebook or Amazon. Not many are able to achieve, what you just did. But, if you want to engage in cutting
edge innovation with Deep Learning and work with us, please do connect.