New software allows non specialists to intuitively train machines using gestures
Many computer systems people interact with on a daily basis require knowledge about certain aspects of the world, or models, to work. These systems have to be trained, often needing to learn to recognize objects from video or image data. This data often contains superfluous content that reduces the accuracy of models. So researchers found a way to incorporate natural hand gestures into the teaching process. This way, users can more easily teach machines about objects, and the machines can also learn more effectively.
You’ve probably heard the term machine learning before, but are you familiar with machine teaching? Machine learning is what happens behind the scenes when a computer uses input data to form models that can later be used to perform useful functions. But machine teaching is the somewhat less explored part of the process, of how the computer gets its input data to begin with. In the case of visual systems, for example ones that can recognize objects, people need to show objects to a computer so it can learn about them. But there are drawbacks to the ways this is typically done that researchers from the University of Tokyo’s Interactive Intelligent Systems Laboratory sought to improve.
“In a typical object training scenario, people can hold an object up to a camera and move it around so a computer can analyze it from all angles to build up a model,” said graduate student Zhongyi Zhou. “However, machines lack our evolved ability to isolate objects from their environments, so the models they make can inadvertently include unnecessary information from the backgrounds of the training images. This often means users must spend time refining the generated models, which can be a rather technical and time-consuming task. We thought there must be a better way of doing this that’s better for both users and computers, and with our new system, LookHere, I believe we have found it.”
Zhou, working with Associate Professor Koji Yatani, created LookHere to address two fundamental problems in machine teaching: firstly, the problem of teaching efficiency, aiming to minimize the users’ time, and required technical knowledge. And secondly, of learning efficiency — how to ensure better learning data for machines to create models from. LookHere achieves these by doing something novel and surprisingly intuitive. It incorporates the hand gestures of users into the way an image is processed before the machine incorporates it into its model, known as HuTics. For example, a user can point to or present an object to the camera in a way that emphasizes its significance compared to the other elements in the scene. This is exactly how people might show objects to each other. And by eliminating extraneous details, thanks to the added emphasis to what’s actually important in the image, the computer gains better input data for its models.
“The idea is quite straightforward, but the implementation was very challenging,” said Zhou. “Everyone is different and there is no standard set of hand gestures. So, we first collected 2,040 example videos of 170 people presenting objects to the camera into HuTics. These assets were annotated to mark what was part of the object and what parts of the image were just the person’s hands. LookHere was trained with HuTics, and when compared to other object recognition approaches, can better determine what parts of an incoming image should be used to build its models. To make sure it’s as accessible as possible, users can use their smartphones to work with LookHere and the actual processing is done on remote servers. We also released our source code and data set so that others can build upon it if they wish.”
Factoring in the reduced demand on users’ time that LookHere affords people, Zhou and Yatani found that it can build models up to 14 times faster than some existing systems. At present, LookHere deals with teaching machines about physical objects and it uses exclusively visual data for input. But in theory, the concept can be expanded to use other kinds of input data such as sound or scientific data. And models made from that data would benefit from similar improvements in accuracy too.
Original Article: Machine learning, from you
More from: University of Tokyo
The Latest Updates from Bing News
Go deeper with Bing News on:
Gesture-based machine learning
- How to always stay in frame on video calls
S etting yourself up for a video call can take a while. To get the frame just right, you may need to stack your laptop on some books, adjust your webcam’s angle, shift your chai ...
- Yolk is a social app where users swap custom live stickers — no text allowed
More specifically, it’s using Apple’s Vision APIs, and on-device machine learning, to power object detection and ... or have a rude hand gesture bop about in front of a still from a hated TV show. The ...
- The 2023 Digital Advertising Predictions That Will Take Off In 2024
In particular, key implementation areas will include automated video generation and adjustments and the use of machine learning models in predicting, understanding and responding to human gestures ...
- Have fun learning opposites
Help your little one to learn about opposites like 'heavy/light', 'fast/slow', 'on/off', 'open/shut'. Challenge them to come up with the opposites by asking them to think about every day situations.
- How to Build Generative AI Agents with Joon Sung Park
To kick off the series, I speak with Joon Sung Park, a Ph.D. student in computer science at Stanford who works at the intersection of human-computer interaction, NLP, and machine learning ... While ...
Go deeper with Bing News on:
- Machine learning innovations and applications in nanotechnology
Machine learning is a fascinating area of artificial intelligence that gives computers the ability to learn and improve from experience without being explicitly programmed for specific tasks. Think of ...
- The most epic sci-fi movie on Netflix reveals a dangerous question about our reality
But he says that this kind of associative machine teaching is “a far cry from [...] embedding content” — or an idea — “in someone's brain” using BCI. Teaching someone to associate with ...
- Government Schools Are Propaganda Machines
In Artis Shepherd’s recent article, which I highly recommend, he aptly detailed the numerous benefits of homeschooling and data showing that homeschooled students—far from being socially stunted, ...
- Get Rich Quick With These 3 Machine Learning Stocks to Buy Now
Today, machine learning is training AI models and applications, teaching them how to collect, collate and communicate information back to us humans. Given the massive potential of AI, machine learning ...
- Sai Anvesh Durvasula: A beacon in the world of artificial intelligence and machine teaching
In the rapidly evolving realm of technology, few stand out as distinctly as Sai Anvesh Durvasula, a distinguished figure in the field of Artificial Intelligence (AI) and Machine Teaching.