Deep Learning

[Spring 2018][NYU]

Invariant Feature Learning

• embed the input non-linearly into a higher dimensional space
• Bring together things that are semantically similar (polling)

Jacobian Matrix

Suppose f : ℝn → ℝm is a function which takes as input the vector x ∈ ℝn and produces as output the vector f(x) ∈ ℝm. Then the Jacobian matrix J of f is an m×n matrix, usually defined and arranged as follows:

Mid-term

• use pytorch to practice gradient computation... verify
• ConvNets: locality and stationarity
• CBOW, descibe in equation, dirgram, loss function... etc.

• Convolution, backprog, gradients...

• no coding questions in midterm