CVIP 2.0
\( \text{Agenda of this Lecture:}\)
Neural Networks have two components:
You can experiment with simple neural networks at Tensorflow Playground
Usually extracted features are of
lower dimension than data (x)
but, what does it mean when two images are closer to each other?
Closer in Low-Dimensional Feature Space
Simple MLP AutoEncoder
Simple MLP AutoEncoder
Convolutional AutoEncoder
Posterior
Generative Model
Posterior
Generative Model
Training dynamics
1. Draw a batch of real images \( x_i \) with labels \( y_i \).
2. Sample noise \( z_i \) and random labels \( y_i \).
3. Update Discriminator on real \( (x_i,y_i) \) vs. fake \( (G(z_i,y_i),y_i) \).
4. Update Generator to fool \( D\bigl(G(z_i,y_i),y_i\bigr) \) into thinking those fakes are real.