3. Introduction
“There are many interesting recent development in deep
learning…The most important one, in my opinion, is
adversarial training (also called GAN for Generative
Adversarial Networks). This, and the variations that are
now being proposed is the most interesting idea in the
last 10 years in ML, in my opinion.” – Yann LeCun
4. Generative Model
generative models: any model that takes a training set, consisting of samples drawn
from a distribution p_data, and learns to represent an estimate of that distribution
somehow
A discriminative model learns a function that maps the input data (x) to some desired
output class label (y). In probabilistic terms, they directly learn the conditional
distribution P(y|x).
A generative model tries to learn the joint probability of the input data and labels
simultaneously, i.e. P(x,y). This can be converted to P(y|x) for classification via Bayes
rule, but the generative ability could be used for something else as well, such as
creating likely new (x, y) samples.
5. Generative Model
generative models: any model that takes a training set, consisting of samples drawn
from a distribution p_data, and learns to represent an estimate of that distribution
somehow
6. Generative Model
Advantages
• represent and manipulate high-dimensional probability
distributions
• incorporated into reinforcement learning
• can be trained with missing data and can provide predictions
on inputs that are missing data
• enable machine learning to work with multi-modal outputs
• many tasks intrinsically require realistic generation of samples
from some distribution
13. Framework of GANs
• Generator
• One takes noise as input and generates sample
• Discriminator
• receives samples from both the generator and
the training data, and has to be able to
distinguish between the two sources
• Relationship between these two neural
network: Competing
https://ishmaelbelghazi.github.io/ALI
14. How do GANs work
Symbol Meaning
D(x, 𝜃 𝑑) A differentiable function
The probability that x came from the data rather than 𝑝 𝑔
𝜃 𝑑 Parameters of D
𝑝 𝑔 The generator distribution
G(z; 𝜃𝑔) A differentiable function
𝜃𝑔 Parameters of G
z Input noise
𝑃𝑧(z) A prior on input noise variables
Notation
15. How do GANs work
We train D to maximize the probability of assigning the correct label to both
training examples and samples from G.
We simultaneously train G to minimize log(1 − D(G(z))).
Minimax Game:
16. How do GANs work
Cost function for discriminator: 𝐽 𝐷
This is just the standard cross-entropy cost that minimized when
training a standard binary classifier with a sigmoid output.
17. How do GANs work
Cost function for generator: 𝐽 𝐺
Zero-Sum Game ( also called minimax game), in which the sum of all player’s costs
is always zero. So:
18. How do GANs work
Cost function for generator: 𝐽 𝐺
Disadvantages for this cost function: The generator’s gradient vanishes
To solve this problem, we continue to use cross-entropy minimization for the
generator. We just need to flip the sign of the cost function above, and we get:
20. How do GANs work
For each epoch
you only need to do a two-step training.
21. How do GANs work
For each epoch
you only need to do a two-step training.
22. How do GANs work
For each epoch, you only need to do a
two-step training.
23. How do GANs work
https://www.youtube.com/watch?v=0r3g7-
4bMYU&feature=youtu.be
24. Research frontiers
• Non-convergence: Game solving algorithms may not
approach an equilibrium at all
• Mode Collapse: causes low output diversity
• Evaluation: There is not any single compelling way to
evaluate a generative model
• Discrete outputs: G must be differentiable
• Finding equilibria in games: Simultaneous SGD on
two players costs may not converge to a Nash
equilibrium
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation
Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation
Topic Regression Multi-Modal Latent Dirichlet Allocation for Image Annotation