shagunsodhani

Deep Convolutional Generative Adversarial Nets

Introduction

• The paper presents Deep Convolutional Generative Adversarial Nets (DCGAN) - a topologically constrained variant of conditional GAN.
• Link to the paper

Benefits

• Stable to train

shagunsodhani

Generative Adversarial Nets

Introduction

• The paper proposes an adversarial approach for estimating generative models where one model (generative model) tries to learn a data distribution and another model (discriminative model) tries to distinguish between samples from the generative model and original data distribution.
• Link to the paper

Adversarial Net

• Two models - Generative Model(G) and Discriminative Model(D)

shagunsodhani

A Roadmap towards Machine Intelligence

Introduction

• The paper presents some general characteristics that intelligent machines should possess and a roadmap to develop such intelligent machines in small, realistic steps.
• Link to the paper

Ability to Communicate

• The intelligent agents should be able to communicate with humans, preferably using language as the medium.

shagunsodhani

Smart Reply: Automated Response Suggestion for Email

Introduction

• Proposes a novel, end-to-end architecture for generating short email responses.
• Single most important benchmark of its success is that it is deployed in Inbox by Gmail and assists with around 10% of all mobile responses.
• Link to the paper.

Challenges in deploying Smart Reply in a user-facing product

shagunsodhani

# Script to calculate entropy for any column in a file.

from __future__ import print_function

import numpy as np

def entropy(file_path, sep, col_index, col_name):
    '''Method to calculate entropy for any col_index
    in a file where columns are seperated by sep'''
    distribution = np.asarray(list(read_column(file_path, sep, col_index)))

shagunsodhani

Convolutional Neural Network For Sentence Classification

Introduction

• The paper demonstrates how simple CNNs, built on top of word embeddings, can be used for sentence classification tasks.
• Link to the paper
• Implementation

Architecture

shagunsodhani

Topic

Introduction to Deep Learning with Keras

Description

Keras is a high-level neural networks library, written in Python and capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.

In the talk, I would introduce Keras and talk about how it can be used to accomplish workflows like image classfication and sequence modelling.

shagunsodhani

Conditional Image Generation with PixelCNN Decoders

Introduction

• The paper explores the domain of conditional image generation by adopting and improving PixelCNN architecture.
• Link to the paper

Based on PixelRNN and PixelCNN

• Models image pixel by pixel by decomposing the joint image distribution as a product of conditionals.

shagunsodhani

Pixel Recurrent Neural Network

Introduction

• Problem: Building an expressive, tractable and scalable image model which can be used in downstream tasks like image generation, reconstruction, compression etc.
• Link to the paper

Model

• Scan the image, one row at a time and one pixel at a time (within each row).

shagunsodhani

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Introduction

• The paper presents gradient computation based techniques to visualise image classification models.
• Link to the paper

Experimental Setup

• Single deep convNet trained on ILSVRC-2013 dataset (1.2M training images and 1000 classes).