Machine Learning technology is found in everything from spam detection programs to intelligent thermostats, but can the technology make a huge leap to handle the exponentially larger amounts of information and advanced applications of the future?
Researchers from the government's cutting edge research group, the Intelligence Advanced Research Projects Activity (IARPA), certainly hope so and this week announced that they are looking to the industry for new ideas that may become the basis for cutting edge Machine Learning projects.
From IARPA: The focus of our request for information is on recent advances toward automatic machine learning, including automation of architecture and algorithm selection and combination, feature engineering, and training data scheduling for usability by non-experts, as well as scalability for handling large volumes of data. Machine Learning is used extensively in application areas of interest including speech, language, vision, sensor processing and the ability to meld that data into a single, what IARPA calls multi-modal system.
"In many application areas, the amount of data to be analyzed has been increasing exponentially (sensors, audio and video, social network data, web information) stressing even the most efficient procedures and most powerful processors. Most of these data are unorganized and unlabeled and human effort is needed for annotation and to focus attention on those data that are significant," IARPA stated.
IARPA listed a number of questions those interested in developing the Machine Learning project should answer, including:
- What are your proposed methods for (a) automation of architecture and algorithm selection and combination, (b) feature engineering, and (c) training data scheduling? How will these automation methods affect the usability of an analytic system by non-experts?
- What are the compelling reasons to use your proposed approach in a scalable multi-modal analytic system?
- How will your approach handle different time scales, missing data, and sparse data?
- How will your approach be applied to diverse data, such as speech, language, vision, sensor processing, and multi-modal integration?
- How will you supplement training data with real-world and previously learned knowledge?
- Are supporting technologies readily available or does new technology need to be created?
Useful automatic machine learning systems will require significant innovations in the science and technology of machine learning, possibly including (but not limited to) complicated hierarchical architectures like Deep Belief Nets and hierarchical clustering. In the end IARPA says it expects to identify promising areas for investment and it expects to hold a Machine Learning workshop in late March, 2012.
Layer 8 Extra
Check out these other hot stories: