Jeremy Howard: The wonderful and terrifying implications of computers that can learn

Advanced Machine Learning with scikit-learn

My first teaching experience

I would have to say it was definitely a learning experience. I taught a database course to 40 mostly seniors and mostly male students. I spent the semester researching and learning which techniques were best used for teaching. I also learned how to create my own lectures, projects and exams. This experience definitely gave me a taste of what it would be like to teach professionally. I also learned a bit about myself. By the end of the semester I no longer felt uncomfortable with speaking in front of a group or answering questions and challenges on the fly. I also was impressed with many of the students in my class.

Now it is back to research!

And maybe teaching again in the future once I recover from this first one.

Taming Wild Big Data

Our latest paper for the AAAI Fall Symposium.
Abstract: Wild Big Data is data that is hard to extract, understand, and use due to its heterogeneous nature and volume. It typically comes without a schema, is obtained from multiple sources and provides a challenge for information extraction and integration. We describe a way to subduing Wild Big Data that uses techniques and resources that are popular for processing natural language text. The approach is applicable to data that is presented as a graph of objects and relations between them and to tabular data that can be transformed into such a graph. We start by applying topic models to contextualize the data and then use the results to identify the potential types of the graph’s nodes by mapping them to known types found in large open ontologies such as Freebase, and DBpedia. The results allow us to assemble coarse clusters of objects that can then be used to interpret the link and perform entity disambiguation and record linking.

Confidence in Lasso by Jared Lander

Confidence in Lasso by Jared Lander.

Learning Julia

julia is a dynamic programming language getting a bit of attention. I am running a few tutorials and learning the language. Some resources are listed below in case you are interested....

Learn about julia
Quick tutorial
Another tutorial
Google group

Lego Car

This is just too cool, a lego car tha runs on compressed air.

Kano kit

Something to think about...

Source: https://twitter.com/AIIsAwesome/status/404341645509812224/photo/1

Just received notice Qualcomm Toq Smartwatch is available Dec 2nd

Qualcomm Toq Smartwatch is available as of Dec 2nd for a starting cost of $349.99 (OUCHY!).

AAAI Symposium

I've been spending the weekend at the AAAI Symposium. There have been quite a few interesting talks.
John Laird gave an interesting talk on General Intelligence.
Andrew Ng also gave an interesting talk, on Deep Learning.

3D on the Web - Introduction to WebGL

This is an interesting talk offered through ACM.
Supplementary Learning Resources from Alain Chesnais
Collada:
Official website http://collada.org/
Tutorials https://collada.org/mediawiki/index.php/Portal:Tutorials
WebGL:
Official website http://www.khronos.org/webgl/
Tony Parisi's Tutorials http://learningwebgl.com/
Three.js:
Official website http://threejs.org/
Ilmari Heikkinen's Tutorial http://fhtr.org/BasicsOfThreeJS/#2
X3Dom:
Official website http://www.x3dom.org/
Introductory tutorial http://x3dom.org/docs/dev/tutorial/firststeps.html

The Virtual Brain

How it works...

4D Printers

This is pretty cool, researchers are trying to add a 4th dimension to 3D printing. What they are trying to do is print material that can change over time, not just shape, but based on some external stimuli, change of behavior. I find this incredibly interesting.

The article is titled, "’4D printing’ adaptive materials" and is found on kurzweilai.net
Read the article at http://www.kurzweilai.net/4d-printing-adaptive-materials.

A great Ted talk on this same topic:

Google Glass

Our lab, ebiquity, has been playing with Google Glass. So now I am hooked and wondering what sort of app I could develop for Google Glass. I've been doing a little reading on Google glass and came across this blog. The developer, Lance Nanek developed an interesting implementation of panning using head movement.

Watch the video to learn more:


Very cool stuff.

More information for developers is here.

And yet more info for developers.

And if you want Google Glass, then keep up with the latest news.

Mid-Atlantic Student Colloquium on Speech, Language and Learning

UMBC is hosting the Mid-Atlantic Student Colloquium on Speech, Language and Learning.

Register online.

The schedule is now posted.

Snapshot of the schedule:

09:00-09:45 Registration, set up

09:45-10:00 Opening

10:00-11:20 Oral presentations I

Lushan Han, Abhay Kashyap, Tim Finin, James Mayfield and Jonathan Weese (UMBC & JHU). Semantic Textual Similarity Systems

Keith Levin, Aren Jansen and Ben Van Durme (JHU). Toward Faster Audio Search Using Context-Dependent Hashing

Shawn Squire, Monica Babes-Vroman, Marie Desjardins, Ruoyuan Gao, Michael Littman, James MacGlashan and Smaranda Muresan (UMBC & Brown). Learning to Interpret Natural Language Instructions

Viet-An Nguyen, Jordan Boyd-Graber and Philip Resnik (UMCP). Lexical and Hierarchical Topic Regression

11:20-12:10 Poster session I

Posters

12:10-12:40 Lunch

12:40-1:40 Panel

"How to be a successful PhD student and and transition to a great job"
Marie desJardins (UMBC)
Mark Dredze (JHU)
Claudia Pearce (DoD)
Ian Soboroff (NIST)
Hanna Wallach (UMass)


1:50-3:10 Oral presentations II

Qingqing Cai and Alexander Yates (Temple). Large-scale Semantic Parsing via Schema Matching and Lexicon Extension

William Yang Wang and William W. Cohen (CMU). Efficient First-Order Probabilistic Logic Programming for Natural Language Inference

Xuchen Yao, Benjamin Van Durme, Chris Callison-Burch, Peter Clark (JHU & UPenn & AI2). Semi-Markov Phrase-based Monolingual Alignment

Wei Xu, Alan Ritter and Ralph Grishman (NYU). Gathering and Generating Paraphrases from Twitter with Application to Normalization

3:10-4:00 Poster session II

Posters

4:00-5:00 Breakout sessions

NLP in low resource settings, Ann Irvine (JHU)

Dynamic Programming: Theory and Practice, Alexander Rush (Columbia/MIT)

NELL: Never Ending Language Learning, Partha Pratim Talukdar (CMU)

5:00 Closing

5:15 - 7:00 Wine down

Wine and beer at Flat Tuesdays, UMBC Commons

New and Emerging Technologies in Assistive Robotics Slides

Assistive robotics from Wolfgang Heller

Baxter

Originality

“It is better to fail in originality than to succeed in imitation.”
--Herman Melville

Integrity

“Truth at last cannot be hidden. Dissimulation is of no avail. Dissimulation is to no purpose before so great a judge. Falsehood puts on a mask. Nothing is hidden under the sun.” ― Leonardo da Vinci

“Stars hide your fires; let not light see my black and deep desires: The eyes wink at the hand; yet let that be which the eye fears, when it is done, to see” ― William Shakespeare, Macbeth