Reducing the Data Demands of Smart Machines
July 17, 2018 | DARPAEstimated reading time: 2 minutes
Machine learning (ML) systems today learn by example, ingesting tons of data that has been individually labeled by human analysts to generate a desired output. As these systems have progressed, deep neural networks (DNN) have emerged as the state of the art in ML models.
Image Caption: Machine learning systems today learn by example, ingesting tons of data that has been individually labeled by human analysts to generate a desired output. The goal of the LwLL program is to make the process of training machine learning models more efficient by reducing the amount of labeled data required to build a model by six or more orders of magnitude, and by reducing the amount of data needed to adapt models to new environments to tens to hundreds of labeled examples.
DNN are capable of powering tasks like machine translation and speech or object recognition with a much higher degree of accuracy. However, training DNN requires massive amounts of labeled data–typically 109 or 1010 training examples. The process of amassing and labeling this mountain of information is costly and time consuming.
Beyond the challenges of amassing labeled data, most ML models are brittle and prone to breaking when there are small changes in their operating environment. If changes occur in a room’s acoustics or a microphone’s sensors, for example, a speech recognition or speaker identification system may need to be retrained on an entirely new data set. Adapting or modifying a model can take almost as much time and energy as creating one from scratch.
To reduce the upfront cost and time associated with training and adapting an ML model, DARPA is launching a new program called Learning with Less Labels (LwLL). Through LwLL, DARPA will research new learning algorithms that require greatly reduced amounts of information to train or update.
“Under LwLL, we are seeking to reduce the amount of data required to build a model from scratch by a million-fold, and reduce the amount of data needed to adapt a model from millions to hundreds of labeled examples,” said Wade Shen, a DARPA program manager in the Information Innovation Office (I2O) who is leading the LwLL program. “This is to say, what takes one million images to train a system today, would require just one image in the future, or requiring roughly 100 labeled examples to adapt a system instead of the millions needed today.”
To accomplish its aim, LwLL researchers will explore two technical areas. The first focuses on building learning algorithms that efficiently learn and adapt. Researchers will research and develop algorithms that are capable of reducing the required number of labeled examples by the established program metrics without sacrificing system performance. “We are encouraging researchers to create novel methods in the areas of meta-learning, transfer learning, active learning, k-shot learning, and supervised/unsupervised adaptation to solve this challenge,” said Shen.
The second technical area challenges research teams to formally characterize machine learning problems, both in terms of their decision difficulty and the true complexity of the data used to make decisions. “Today, it’s difficult to understand how efficient we can be when building ML systems or what fundamental limits exist around a model’s level of accuracy. Under LwLL, we hope to find the theoretical limits for what is possible in ML and use this theory to push the boundaries of system development and capabilities,” noted Shen.
Suggested Items
Reducing Nitrogen Consumption in Convection Soldering with Rehm Thermal Systems' Patented Mechatronic Curtain
03/28/2024 | Rehm Thermal SystemsCurrent developments indicate a need for larger throughput heights due to the trend towards e-mobility, which in turn increases nitrogen consumption for process inertization. Rehm Thermal Systems responds to this issue with an innovative solution: the mechatronic curtain.
Intel Announces New Program for AI PC Software Developers and Hardware Vendors
03/27/2024 | Intel CorporationIntel Corporation announced the creation of two new artificial intelligence (AI) initiatives as part of the AI PC Acceleration Program: the AI PC Developer Program and the addition of independent hardware vendors to the program.
SEMI ESD Alliance 2024 CEO Executive Outlook to Explore the Evolving RISC-V Movement and Semiconductor Design Ecosystem
03/27/2024 | SEMIKey executives from leading semiconductor EDA and IP companies will gather to discuss the latest industry trends, challenges and opportunities Thursday, May 9, in Santa Clara, California at the annual CEO Executive Outlook, hosted by the Electronic System Design Alliance (ESD Alliance), a SEMI Technology Community, and Keysight Technologies. Registration opens soon.
CentraTEQ to Showcase Wide Range of Vibration & Environmental Test Systems at Battery Tech Expo 24
03/26/2024 | CentraTEQEnvironmental and vibration test specialists CentraTEQ are excited to be exhibiting at the upcoming Battery Tech Expo, scheduled to take place at Silverstone on April 25, 2024.
SEMI 3D & Systems Summit To Spotlight Trends In Hybrid Bonding, Chiplet Design And Environmental Sustainability
03/26/2024 | SEMILeading experts in 3D integration and systems for semiconductor manufacturing applications will gather at the annual SEMI 3D & Systems Summit, 12-14 June, 2024,