Researchers at MIT and IBM assemble new object recognition dataset that highlights the limitations of current AI techniques

Average importance

The dataset consisted of an assortment of objects shot at unusual angles and surrounded by clutter. While computer vision performance has increased significantly over the past decade, a top-performing algorithm's accuracy rates fell from a high of 97% on more simple datasets to just 50% to 55% on the new dataset. This study highlights a major challenge for AI, namely, that as the environment becomes more complex and unpredictable, machine learning performance drops off considerably. While clients could wait for the algorithms to become more robust before deploying a solution, a more near-term solution to this challenge is to consider constraining a problem to make it a better fit for today's tools.

For the original news article, click here .

Further Reading

Natural Language Processing

Technology | January 07, 2021

Tools and techniques, including machine learning, to process, analyze, and generate text. Not part of subscription

Automated Inspection Systems

Technology | January 19, 2021

Systems that perform automated nondestructive testing (NDT) of products or routine inspections of infrastructure in physical industries. Not part of subscription

U.S. Air Force selects Black Swift to predict drone failures before they happen

News Commentary | April 05, 2021

The U.S. Air Force was facing reliability issues and dozens of crashes on its Unmanned Aircraft Systems (UAS). To improve on identifying potential failures, the agency has awarded Black Swift Technologies an SBIR Grant to develop a solution for predicting UAS maintenance schedules. The system uses ... Not part of subscription