Deep Learning Coursera - Course 1
Supervised Learning - examples [Input(x), Output(y), Application] - Answer 1)
Home Features, Price, Real Estate (NN)
2) Ad user info, Click on Ad?(0/1), Online Advertising (NN)
3) Image, Object (1, ..., 1000), Photo Tagging (CNN)
4) Audio, Text transparent, Speech recognition (RNN)
5) English, Chinese, Machine translation (RNN)
6) Image Radar info, Position of other cars, Autonomous driving (custom
hybrid)
Structured Data - examples (Supervised Learning) - Answer 1) Housing Data
(size, #bedrooms) --> Price of House (1000$)
2) (User Age, Ad ID) --> Click (1/0)
Unstructured Data - examples (Supervised Learning) - Answer 1) Audio
(waves)
2) Image (cat)
3) Text (Four scores and seven years ago...) ... ex: invidual words =
unstructured data
Backaward Propogation - Answer One step of (backward propagation) yields
derivative of final output variable
dvar (for pupose of this course) - Answer refers to derivative of the final
ouput variable
simplified formula for the (derivative of the loss with respect to z) - Answer a
- z
dw - why only 1 such derivative in output from this for loop? - Answer
because derivative (dw) is cumulative
Non-Vectorized - Answer z = w.T*x + b
Non-vectorized:
z = 0
for i in range(n-x):
z += w[i] ** [:]
