lab 1: unsupervised pre-training, dropout and representation learning

@tachyeonz : For my first set of Pauli Space experiments, I thought I would start by attempting to answer elementary questions which might lead to more data efficient deep models and algorithms.

Read More

Connect On:
Twitter :@tachyeonz

On the intuition behind deep learning & GANs — towards a fundamental understanding

@tachyeonz : A generative adversarial network (GAN) is composed of two separate networks – the generator and the discriminator. It poses the unsupervised learning problem as a game between the two. In this post we will see why GANs have so much potential, and frame GANs as a boxing match between two opponents.

Read More

Connect On:
Twitter :@tachyeonz

Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch)

@tachyeonz : In 2014, Ian Goodfellow and his colleagues at the University of Montreal published a stunning paper introducing the world to GANs, or generative adversarial networks.

Read More

Connect On:
Twitter :@tachyeonz

Graph-powered Machine Learning at Google

@tachyeonz : Much of the recent success in deep learning, and machine learning in general, can be attributed to models that demonstrate high predictive capacity when trained on large amounts of labeled data — often millions of training examples.

Read More

Connect On:
Twitter :@tachyeonz

Unsupervised learning of 3D structure from images

@tachyeonz : Unsupervised learning of 3D structure from images Rezende et al. (Google DeepMind) NIPS,2016 Earlier this week we looked at how deep nets can learn intuitive physics given an input of objects and the relations between them. If only there was some way to look at a 2D scene (e.g.

More

Published On:January 10, 2017 at 09:21AM

Connect On:
Medium : http://www.medium.com/iiot
Twitter :@tachyeonz

Game Theory Reveals the Future of Deep Learning

@tachyeonz : If you’ve been following my articles up to now, you’ll begin to perceive, what’s apparent to many advanced practitioners of Deep Learning (DL), is the emergence of Game Theoretic concepts in the design of newer architectures. This makes intuitive sense for two reasons.

More

Tags : adversarial networks, deep learning, discriminant, game theory, gans, neural networks, unsupervised learning, yann le cun, z

Published On:January 05, 2017 at 01:17AM

Connect On:
Medium : http://www.medium.com/iiot
Twitter :@tachyeonz

Clustering the Threat Landscape

@tachyeonz : Much of threat intelligence is grouping together information to identify common traits in attackers. To that end, I wrote a quick python script to identify common indicators in reports in Alienvault’s OTX platform.

More

Tags : alienvault otx, classification, clustering, cyber security, cyberwarfare, cyberweapons, dataviz, hacking, landscape, machine learning, malawares, malicious ip, pentest, pentesting, python, signatures, threatcrowd, unsupervised learning, virus, z

Published On:March 29, 2016 at 03:03PM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz

Apple leaps into AI research with improved simulated + unsupervised learning

@tachyeonz : Corporate machine learning research may be getting a new vanguard in Apple. Six researchers from the company’s recently formed machine learning group published a paper that describes a novel method for simulated + unsupervised learning.

More

Tags : apple, artificial intelligence, gans, generative adversarial, m, machine learning, networks, news, research paper, russ salakhutdinov, simulated, simulated gans, technology, unsupervised learning

Published On:December 27, 2016 at 06:45PM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz

NIPS 2016 Review, Day 1

@tachyeonz : Ever the scientists, the two organizers justified their choice on the program committee by maintaining that they want to grow the number submissions while decreasing bias and variance. They treated the problem with unknown ground truth of what the “best papers” were,

More

Tags : artificial intelligence, cnn, conference, convolution neural net, deep learning, gans, lstm, m, machine learning, meta learning, meta models, nips2016, phased lstm, recurrent neuralnet, reinforcement learning, rnn, time series data, unsupervised learning, yann le cun

Published On:December 25, 2016 at 07:26PM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz

A Tour of Machine Learning Algorithms

@tachyeonz : In this post, we take a tour of the most popular machine learning algorithms. It is useful to tour the main algorithms in the field to get a feeling of what methods are available. It is useful to tour the main algorithms in the field to get a feeling of what methods are available.

Click here to read more

Tags : #ai, #algorithms, #machinelearning, #python, #supervisedlearning, #tutorials, #unsupervisedlearning, m

Published On:December 05, 2016 at 06:35AM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz

To supervise or not to supervise in AI?

@tachyeonz : To learn more about opportunities in applied AI, join us at the O’Reilly Artificial Intelligence Conference, September 26-27, 2016 in New York. One of the truisms of modern AI is that the next big step is to move from supervised to unsupervised learning.

Click here to read more

Tags : #ai, #comparison, #machinelearning, #supervisedlearning, #unsupervisedlearning, m

Published On:November 09, 2016 at 11:56PM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz

Beginner’s Guide to Unsupervised Learning

@tachyeonz : The majority of machine learning posts to date on QuantStart have all been about supervised learning. In this post we are going to take a look at unsupervised learning, which is a far more challenging area of machine learning.

Click here to read more

Tags : #datascience, #machinelearning, #unsupervisedlearning, guide, m

Published On:August 11, 2016 at 09:06PM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz