“TRANSFER LEARNING” From The Harvard Business Review – using the recent Presidential Election & lack of data to illustrate Transfer Learning: “a field that helps to solve these problems by offering a set of algorithms that identify the areas of knowledge which are “transferable” to the target domain. This broader set of data can […]
Edu-Video | “EDWARD”: A Library for Probabilistic Modeling, Inference, and Criticism | ML NYC Meetup
“Edward”: A library for probabilistic modeling, inference, and criticism Abstract https://www.meetup.com/NYC-Machine-Learning/events/236943279/ http://www.zentation.com/viewer2/webcast/NAPNgdDUBF/Dustin-Tran—Spotify-Talk-(2017-01-19) Probabilistic modeling is a powerful approach for analyzing empirical information. In this talk, I will provide an overview of Edward, a software library for probabilistic modeling. Formally, Edward is a probabilistic programming system built on computational graphs,supporting compositions of both models and inference […]
Edu-Video |”Building a Production Machine Learning Infrastructure” – Josh Wills /Dir. Data Scientist
(Reposted due to popular demand) Another great video from Josh Wills. Josh is Sr. Director of Data Science at Cloudera and has a gift for making fairly complicated technology explanations very digestible to the novice and intermediary techie.
What I most love about this video is how Josh explains -very clearly – the issue of translating analytics Machine Learning on a large set of data records (many individuals) and making it work well in a “real life” production environment on a single individual (think eCommerce). Watch Video
Great (free) Machine Learning course for beginners by Caltech University. Introduction to; supervised, unsupervised, and reinforcement learning. Components of the learning problem. Lectures 1 of 18 of Caltech’s Machine Learning Course – CS 156 by Professor Yaser Abu-Mostafa. Watch Video
VIDEO | Dr. Andy Feng, VP Architecture at Yahoo! | “Large-Scale Machine Learning” | 2016 CSL Student Conference
The University of Illinois’ Coordinated Science Laboratory had it student run conference last month. This video is Dr. Andy Feng – VP Architecture at Yahoo! He leads the architecture and design of big data and machine learning initiatives. “In this talk, we illustrate Yahoo use cases and datasets, and explain the evolution of big-data technology stack.” Watch Video
In this Video by Ryan Compton, Head of Data Science at Clarifai, talks about using convolutional neural networks to deal with the problem of nudity detection. Watch Video
VIDEO | NYC Machine Learning Meetup 2016 | Dan Melamed “How To Learn From What Your Users Might Not See”
At the Machine Learning Meetup in NYC, Dan Melamed gave a machine learning talk titled: “How To Learn From What Your Users Might Not See”. This talk will focus on contextual bandits and their applications.
In this tutorial, Dan will show how to learn from such data in a principled, efficient, and unbiased manner. The techniques that he will describe were largely responsible for a click-thru rate gain of over 25% on MSN.com. Watch Video
The 20th anniversary of the GOTO Copenhagen Conference took place last month. Two 50 Minute videos – Machine Learning and Deep Learning. READ MORE
Machine Learning is at the core of data science and we see it’s applications all over now (i.e. recommender engines, etc.). As Pedro Domingos’s Professor of Computer Science U. Washington writes in the piece, “In reality, the main purpose of machine learning is to predict the future.” It’s important to be aware of the MYTHs associated with Machine Learning. Read More
Kaggle is a community of almost 450K data scientists who have built nearly 2 million machine learning models to participate in its competitions. Data scientists come to Kaggle to learn, collaborate and develop the state of the art in machine learning. This talk will cover some of the lessons on winning techniques we have learned from the Kaggle community. Watch Video