Nand Kishor Contributor

Nand Kishor is the Product Manager of House of Bots. After finishing his studies in computer science, he ideated & re-launched Real Estate Business Intelligence Tool, where he created one of the leading Business Intelligence Tool for property price analysis in 2012. He also writes, research and sharing knowledge about Artificial Intelligence (AI), Machine Learning (ML), Data Science, Big Data, Python Language etc... ...

Full Bio 
Follow on

Nand Kishor is the Product Manager of House of Bots. After finishing his studies in computer science, he ideated & re-launched Real Estate Business Intelligence Tool, where he created one of the leading Business Intelligence Tool for property price analysis in 2012. He also writes, research and sharing knowledge about Artificial Intelligence (AI), Machine Learning (ML), Data Science, Big Data, Python Language etc...

3 Best Programming Languages For Internet of Things Development In 2018
429 days ago

Data science is the big draw in business schools
602 days ago

7 Effective Methods for Fitting a Liner
612 days ago

3 Thoughts on Why Deep Learning Works So Well
612 days ago

3 million at risk from the rise of robots
612 days ago

Top 10 Hot Artificial Intelligence (AI) Technologies
317691 views

Here's why so many data scientists are leaving their jobs
82266 views

2018 Data Science Interview Questions for Top Tech Companies
80310 views

Want to be a millionaire before you turn 25? Study artificial intelligence or machine learning
78189 views

Google announces scholarship program to train 1.3 lakh Indian developers in emerging technologies
62865 views

What Should Beginners Know About Adversarial Machine Learning?

By Nand Kishor |Email | Jul 26, 2017 | 7230 Views

What should people new to the field know about adversarial machine learning? originally appeared on Quora - the place to gain and share knowledge, empowering people to learn from others and better understand the world.

Answer by Alexey Kurakin, Research Engineer at Google Brain, on Quora:
In the first place, to understand the context of adversarial machine learning, you should know about Machine Learning and Deep Learning in general.

Adversarial machine learning studies various techniques where two or more sub-components (machine learning classifiers) have an opposite reward (or loss function). Most typical applications of adversarial machine learning are: GANs and adversarial examples. You may also find applications of this approach in other machine learning papers.

In GAN (generative adversarial network) you have two networks: generator and discriminator. The goal of the generator is to generate realistic samples and the goal of discriminator is to tell generated and real samples apart.

Adversarial examples are slightly perturbed input samples which cause misclassification. Adversarial examples are usually considered in the context of machine learning robustness and security. The two sub-components with opposite rewards are following. There is a machine learning classifier which is usually optimized to achieve high accuracy and good generalization, and there is an adversary which the goal is to fool a machine learning classifier by perturbing the input.

If you want more information, there is a github page with a good selection of papers and reading materials on adversarial machine learning: yenchenlin/awesome-adversarial-machine-learning.

This question originally appeared on Quora - the place to gain and share knowledge, empowering people to learn from others and better understand the world. You can follow Quora on Twitter, Facebook, and Google+. More questions:




Source: Forbes