Busting the hype and Deconstructing the Hyperparameters of Generative models

Generative models have progressed substantially in the past few years. There has been a substantial proof point of success around image synthesis and
topic extraction and fast information retrieval or filtering.

Flow Models, Autoregressive Models and Generative Adversarial Networks(GANs) are popular generative models are an active area of research.

Roughly speaking, Flow Models apply a stack of invertible transformations to a sample from a prior so that exact log-likelihoods of observations can be computed. On the other hand, Autoregressive Models factorize the distribution over observations into conditional distributions and process one component of the observation at a time.

A Generative Adversarial Network relies on two neural networks namely Generator Neural Network and Discriminator Neural Network that contest and compete with each other in a zero-sum game framework.
The Generator Network takes a random input and tries to generate a sample of data. It then generates data which is then fed into a discriminator network. The task of Discriminator Network is to take input either from the real data or from the generator and try to predict whether the input is real or generated.

The presentation will take a conceptual yet hands-on approach to explore Generative models and discuss the trade-Offs Between GANs and other Generative Models.

 
4 favorite thumb_down thumb_up 0 comments visibility_off  Remove from Watchlist visibility  Add to Watchlist
 

Outline/Structure of the Tutorial

The focus of this session will be around Flow Models and GANs. The first algorithm will cluster review dataset from YELP https://www.yelp.com/dataset/challenge and would then find the clusters of interest that can be generated from the review data. The will then be visualized via t-SNE and we will then evaluate the latent topics embedded within the text.

The second algorithm will focus on GANs and would attempt to generate different styles that can be generated from the fashion data. The focus would be on the new styles that can be generated and detailed explanation on the roles of Generator Network and Discriminator Network.

We will then discuss the trade-offs between the two algorithms and the potential use cases for both. Overall the talk will be structured as follows.

Part 1: Clustering and Topic modeling onYELP dataset

  • Understanding Flow Model.
  • Importance of Machine Learning Model Interpretation
  • Criteria for Model Interpretation Methods
  • Scope of Model Interpretation
  • Visualization using t-SNE

Part 2: Generating Neural style on Fashion Data

  • Understanding Generative Adversarial Model.
  • Generating new styles.
  • Result interpretation and visualization.

Part 3: Discussing the trade-off and potential use cases.

Learning Outcome

Key Takeaways from this talk\tutorial

- Understand what are Generative Models

- Learn the latest and best techniques for building Flow models and GANs

- Learn how to leverage state-of-the-art model interpretation frameworks in Python

- Understand how to interpret models on both structured and unstructured data and visualization techniques

Target Audience

Data Scientists, Engineers, Managers, AI Enthusiasts

Prerequisites for Attendees

Participants are expected to know what is AI, Machine Learning and Deep Learning. Some basics around the Data Science lifecycle including data, features, modeling, and evaluation. Its a hands-on session with two Jupyter Notebook, using Python, so having a basic knowledge of Python would help.

schedule Submitted 2 days ago

Public Feedback

comment Suggest improvements to the Speaker