Fun LoL to Teach Machines How to Learn More Efficiently
May 30, 2016 | DARPAEstimated reading time: 3 minutes
It’s not easy to put the intelligence in artificial intelligence. Current machine learning techniques generally rely on huge amounts of training data, vast computational resources, and a time-consuming trial and error methodology. Even then, the process typically results in learned concepts that aren’t easily generalized to solve related problems or that can’t be leveraged to learn more complex concepts. The process of advancing machine learning could no doubt go more efficiently—but how much so? To date, very little is known about the limits of what could be achieved for a given learning problem or even how such limits might be determined. To find answers to these questions, DARPA recently announced its Fundamental Limits of Learning (Fun LoL) program. The objective of Fun LoL is to investigate and characterize fundamental limits of machine learning with supportive theoretical foundations to enable the design of systems that learn more efficiently.
“We’ve seen advances in machine learning and AI enabling computers to beat human champions playing games like Jeopardy, chess, and most recently Go, the ancient Chinese strategy game,” said Reza Ghanadan, DARPA program manager. “What’s lacking, however, is a fundamental theoretical framework for understanding the relationships among data, tasks, resources, and measures of performance—elements that would allow us to more efficiently teach tasks to machines and allow them to generalize their existing knowledge to new situations. With Fun LoL we’re addressing how the quest for the ultimate learning machine can be measured and tracked in a systematic and principled way.”
As it stands now with machine learning, Ghanadan noted, even a small change in task often requires programmers to create an entirely new machine teaching process. “If you slightly tweak a few rules of the game Go, for example, the machine won’t be able to generalize from what it already knows. Programmers would need to start from scratch and re-load a data set on the order of tens of millions of possible moves to account for the updated rules.”
These kinds of challenges are especially pressing for the Department of Defense, whose specialized systems typically don’t have large training sets to begin with and can’t afford to rely on trial and error methods, which come at high cost. Additionally, defense against complex threats requires machines to adapt and learn quickly, so it is important that they be able to generalize creatively from previously learned concepts.
Fun LoL seeks information regarding mathematical frameworks, architectures, and methods that would help answer questions such as:
- What are the number of examples necessary for training to achieve a given accuracy performance? (e.g., Would a training set with fewer than the 30 million moves that programmers provided to this year’s winning machine have sufficed to beat a Go grand champion? How do you know?)
- What are important trade-offs and their implications? (e.g., size, performance accuracy, processing power considerations)
- How “efficient” is a given learning algorithm for a given problem?
- How close is the expected achievable performance of a learning algorithm compared to what can be achieved at the limit?
- What are the effects of noise and error in the training data?
- What are the potential gains possible due to the statistical structure of the model generating the data?
As an historical example of what Fun LoL is trying to achieve, Ghanadan pointed to a mathematical construct called Shannon’s theorem that helped revolutionize communications theory. Shannon's theorem established a mathematical framework showing that for any given communication channel, it is possible to communicate information nearly error-free up to a computable maximum rate through that channel. The theorem addresses tradeoffs in bandwidth, source data distribution, noise, methods of communication transmission, error correction coding, measures of information, and other factors that can affect determinations of communications efficiency. “Shannon’s theorem provided the fundamental basis that catalyzed the widespread operational application of modern digital and wireless communications,” Ghanadan said. “The goal of Fun LoL is to achieve a similar mathematical breakthrough for machine learning and AI.”
DARPA’s Fun LoL is seeking information that could inform novel approaches to this problem. Technology areas that may be relevant include information theory, computer science theory, statistics, control theory, machine learning, AI, and cognitive science.
Suggested Items
KIC’s Miles Moreau to Present Profiling Basics and Best Practices at SMTA Wisconsin Chapter PCBA Profile Workshop
01/25/2024 | KICKIC, a renowned pioneer in thermal process and temperature measurement solutions for electronics manufacturing, announces that Miles Moreau, General Manager, will be a featured speaker at the SMTA Wisconsin Chapter In-Person PCBA Profile Workshop.
The Drive Toward UHDI and Substrates
09/20/2023 | I-Connect007 Editorial TeamPanasonic’s Darren Hitchcock spoke with the I-Connect007 Editorial Team on the complexities of moving toward ultra HDI manufacturing. As we learn in this conversation, the number of shifting constraints relative to traditional PCB fabrication is quite large and can sometimes conflict with each other.
Standard Of Excellence: The Products of the Future
09/19/2023 | Anaya Vardya -- Column: Standard of ExcellenceIn my last column, I discussed cutting-edge innovations in printed circuit board technology, focusing on innovative trends in ultra HDI, embedded passives and components, green PCBs, and advanced substrate materials. This month, I’m following up with the products these new PCB technologies are destined for. Why do we need all these new technologies?
Experience ViTrox's State-of-the-Art Offerings at SMTA Guadalajara 2023 Presented by Sales Channel Partner—SMTo Engineering
09/18/2023 | ViTroxViTrox, which aims to be the world’s most trusted technology company, is excited to announce that our trusted Sales Channel Partner (SCP) in Mexico, SMTo Engineering, S.A. de C.V., will be participating in SMTA Guadalajara Expo & Tech Forum. They will be exhibiting in Booth #911 from the 25th to the 26th of October 2023, at the Expo Guadalajara in Jalisco, Mexico.
Intel Unveils Industry-Leading Glass Substrates to Meet Demand for More Powerful Compute
09/18/2023 | IntelIntel announced one of the industry’s first glass substrates for next-generation advanced packaging, planned for the latter part of this decade.