John Langford – Page 7 – Machine Learning (Theory)

2/24/2016

Learning to avoid not making an AI

Building an AI is one of the most subtle things people have ever attempted with strong evidence provided by the durable nature of the problem despite attempts by many intelligent people. In comparison, putting a man on the moon was a relatively straightforward technical problem with little confusion about the nature of the solution.

Building an AI is almost surely a software problem since the outer limit for the amount of computation in the human brain is only 10^17 ops/second (10^11 neurons with 10^4 connections operating at 10^2 Hz) which is within reach of known systems.

People tend to mysticize the complexity of unknown things, so the “real” amount of computation required for a human scale AI is likely far less—perhaps even within reach of a 10^13 flop GPU.

Since building an AI is a software problem, the problem is complexity in a much stronger sense than for most problems. The effective approach for dealing with complexity is to use modularity. But which modularity? A sprawl of proposed kinds of often incompatible and obviously incomplete modularity exists. The moment when you try to decompose into smaller problems is when the difficulty of solution is confronted.

For guidance, we can consider what works and what does not. This is tricky, because the definition of AI is less than clear. I qualify AI with by degrees of intelligence in my mind—a human level AI is one which can accomplish the range of tasks which a human can. This includes learning complex things (language, reasoning, etc…) from a much more basic state.

The definition seems natural but it is not easily tested via the famous Turing Test. For example, you could imagine a Cyc-backed system passing a Turing Test. Would that be a human-level AI? I’d argue ‘no’, because the reliance on a human-crafted ontology indicates an incapability to discover and use new things effectively. There is a good science fiction story to write here where a Cyc-based system takes over civilization but then gradually falls apart as new relevant concepts simply cannot be grasped.

Instead of AI facsimiles, learning approaches seem to be the key to success. If a system learned from basic primitives how to pass the Turing Test, I would naturally consider it much closer to human-level AI.

We have seen the facsimile design vs. learn tension in approaches to AI activities play out many times with the facsimile design approach winning first, but not always last. Consider Game Playing, Driving, Vision, Speech, and Chat-bots. At this point the facsimile approach has been overwhelmed by learning in Vision and Speech while in Game Playing, Driving, and Chat-bots the situation is less clear.

I expect facsimile approaches are one of the greater sources of misplaced effort in AI and that will continue to be an issue, because it’s such a natural effort trap: Why not simply make the system do what you want it to do? Making a system that works by learning to do things seems a rather indirect route that surely takes longer and requires more effort. The answer of course is that the system which learns what might otherwise be designed can learn other things as needed, making it inherently more robust.

1/26/2016

New York Machine Learning Deadlines

There’s a number of different Machine Learning related paper deadlines that may interest.

January 29 (abstract) for March 4	New York ML Symposium	Register early because NYAS can only fit 300.
January 27 (abstract)/February 2 (paper) for July 9-15	IJCAI	The biggest AI conference
February 5(paper) for June 19-24	ICML	Nina and Kilian have 850 well-vetted reviewers. Marek and Peder have increased space to allow 3K people.
February 12(paper) for June 23-26	COLT	Vitaly and Sasha are program chairs.
February 12(proposal) for June 23-24	ICML workshops	Fei and Ruslan are the workshop chairs. I really like workshops.
February 19(proposal) for June 19	ICML tutorials	Bernhard and Alina have invited a few tutorials already but are saving space for good proposals as well.
March 1(paper) for June 25-29	UAI	Jersey City isn’t quite New York, but it’s close enough 🙂
May ~2 for June 23-24	ICML workshops	Varies with the workshop.

12/14/2015

Interesting things at NIPS 2015

NIPS is getting big. If you think of each day as a conference crammed into a day, you get a good flavor of things. Here are some of the interesting things I saw.

Grammar as a foreign language. Essentially, attention model + LSTM + a standard dataset = good parser.
A New View of Predictive State Methods for Dynamical System Learning. Predicting future from past and future+1 from past allows you to form an estimate of system dynamics.
Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing (Much) better labeling by better incentives.
Hidden Technical Debt in Machine Learning Systems. A somewhat less vivid title than the earlier one which is entirely worth reading if you worry about ML systems.
Bandits with Unobserved Confounders: A Causal Approach. In systems where a ‘default action’ exists, the act of intervening is not so simple.
The Self-normalized Estimator for Counterfactual Learning. A good idea for reducing variance contextual bandit situations.
Character-level Convolutional Networks for Text Classification. Extensive empirical experiments showing that character alphabets can be effective for NLP tasks.
Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning. A yet-tighter form of RL MDP learning.
On Elicitation Complexity. How many questions do you need to ask to get answers to questions about distributions? This has strong implications on learning algorithm design.
End-to-End Memory Networks. There are not many algorithms for coherently forming pools of memory and using them to answer questions.
Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets. Another way to add memory to a learning system.
Scalable Semi-Supervised Aggregation of Classifiers. Better results for classifier aggregation in transductive settings.

Two other notable events happened during NIPS.

The Imagenet challenge and MS COCO results came out. The first represents a significant improvement over previous years (details here).
The Open AI initiative started. Concerned billionaires create a billion dollar endowment to advance AI in a public(NOT Private) way. What will be done better than NSF (which has a similar(ish) goal)? I can think of many possibilities.

CNTK and Vowpal Wabbit tutorials at NIPS

Both CNTK and Vowpal Wabbit have pirate tutorials at NIPS. The CNTK tutorial is 1 hour during the lunch break of the Optimization workshop while the VW tutorial is 1 hour during the lunch break of the Extreme Multiclass workshop. Consider dropping by either if interested.

CNTK is a deep learning system started by the speech people who started the deep learning craze and grown into a more general platform-independent deep learning system. It has various useful features, the most interesting of which is perhaps efficient scalable training. Using GPUs with allreduce and one-bit sgd it achieves both high efficiency and scalability over many more GPUs than could ever fit into a single machine. This capability is unique amongst all open deep learning codebases so everything else looks nerfed in comparison. CNTK was released in April so this is the first chance for many people to learn about it. See here for more details.

The Vowpal Wabbit tutorial just focuses on what is new this year.

The learning to search framework has greatly matured and is now easily used to solve ad-hoc joint(structured) prediction problems. The ICML tutorial covers algorithms/analysis so this is about using the system.
VW has also become the modeling element of a larger system (called the decision service) which gathers data and uses it as per Contextual Bandit learning. This is now generally usable, and is the first general purpose system of this sort.

10/30/201510/30/2015

ICML 2016 in NYC and KDD Cup 2016

ICML 2016 is in New York City. I expect it to be the largest ICML by far given the destination—New York is the place which is perhaps easiest to reach from anywhere in the world and it has the largest machine learning meetup anywhere in the world.

I am the general chair this year, which is light in work but heavy in responsibilities. Some things I worry about:

How many people will actually come? Numbers are difficult to guess with the field growing and the conference changing locations. I believe we need capacity for at least 3000 people based on everything I know.
New York is expensive. What can be done about it? One thought is that we should actively setup a roommate finding system so the costs of hotels can be shared. Up to 3 people can share a hotel room for the conference hotel (yes, each with their own bed), and that makes the price much more reasonable. I’m also hoping donations will substantially defray the cost. If others have creative ideas, I’m definitely interested.

Markus Weimer also points out the 2016 KDD Cup which has a submission deadline of December 6. KDD Cup datasets have become common reference for many machine learning papers, so this is a good way to get your problem solved well by many people.