https://github.com/mattya/chainer-DCGAN
Ledig, C., Theis, L., Huszar, F., Caballero, J., Aitken, A. P., Tejani, A., Totz, J., Wang, Z., and Shi, W. (2016).
Model the distribution of individual classes
p(x,y)
Learn the (hard or soft) boundary between classes
p(y|x)
Classification:
"The process of classification discards most of the information in the input and produces a single output"
(from Goodfelow book)
An example of
Sampling:
"The model generates new samples from the distribution p(x). This requires a good model of the entire input"
(from Goodfelow book)
An example of
(from Goodfelow book)
George
Danielle
x~Pdata
George
Danielle
x~Pdata
x'=G(z)
z~uniform(0,1)
maximize D1, minimize D2
maximize D2
* D1 and D2 outputs is [0,1]
George
Danielle
x~Pdata
* D1 and D2 outputs is [0,1]
obj_d=tf.reduce_mean(tf.log(D1)+tf.log(1-D2))
opt_d=tf.train.GradientDescentOptimizer(0.01)
.minimize(1-obj_d,global_step=batch,var_list=theta_d)
obj_g=tf.reduce_mean(tf.log(D2))
opt_g=tf.train.GradientDescentOptimizer(0.01)
.minimize(1-obj_g,global_step=batch,var_list=theta_g)
Shay - I think we can let this go (boring, we got the point) -
StreetView House Numbers dataset (SVHN)(Netzer et al., 2011)
Same feature extraction pipeline used for CIFAR-10.
Supervised CNN with the same architecture on the same data achieves a signficantly higher 28.87% validation error.