“Hey Siri, how’s my hair?”
Your smartphone may soon be able to give you an honest answer, thanks to a new machine learning algorithm designed by U of T Engineering researchers Parham Aarabi (ECE) and Wenzhi Guo (ECE MASc 1T5).
The team designed an algorithm that learns directly from human instructions, rather than an existing set of examples, and outperformed conventional methods of training neural networks by 160 per cent. But more surprisingly, their algorithm also outperformed its own training by nine per cent — it learned to recognize hair in pictures with greater reliability than that enabled by the training, marking a significant leap forward for artificial intelligence.
Aarabi and Guo trained their algorithm to identify people’s hair in photographs — a much more challenging task for computers than it is for humans.
“Our algorithm learned to correctly classify difficult, borderline cases — distinguishing the texture of hair versus the texture of the background,” says Aarabi. “What we saw was like a teacher instructing a child, and the child learning beyond what the teacher taught her initially.”
Humans “teach” neural networks — computer networks that learn dynamically — by providing a set of labeled data and asking the neural network to make decisions based on the samples it’s seen. For example, you could train a neural network to identify sky in a photograph by showing it hundreds of pictures with the sky labeled.
This algorithm is different: it learns directly from human trainers. With this model, called heuristic training, humans provide direct instructions that are used to pre-classify training samples rather than a set of fixed examples. Trainers program the algorithm with guidelines such as “Sky is likely to be varying shades of blue,” and “Pixels near the top of the image are more likely to be sky than pixels at the bottom.”
Their work is published in the journal IEEE Transactions on Neural Networks and Learning Systems.
This heuristic training approach holds considerable promise for addressing one of the biggest challenges for neural networks: making correct classifications of previously unknown or unlabeled data. This is crucial for applying machine learning to new situations, such as correctly identifying cancerous tissues for medical diagnostics, or classifying all the objects surrounding and approaching a self-driving car.
“Applying heuristic training to hair segmentation is just a start,” says Guo. “We’re keen to apply our method to other fields and a range of applications, from medicine to transportation.”
The Latest on: AI algorithm heuristic training
via Google News
The Latest on: AI algorithm heuristic training
- Trump's AI Policy: Leave It To The Military And Corporationson February 28, 2020 at 4:41 am
Trump's AI policy edicts are, fortunately, not actively destructive, but they fail to be proactive in the guidance of AI research, development and deployment in beneficial directions.
- Can't Define AI? Try Defining Intelligenceon February 27, 2020 at 7:28 pm
Turns out that the answer to the question of AI’s definition is complicated by one fact: we don’t have a precise definition of intelligence itself.
- Clearview AI leak names businesses using its facial recognition databaseon February 27, 2020 at 4:03 pm
But recent advances in processing systems as well as an explosion of available training data have rapidly advanced the state of the art in the past few years. Today, thanks to advanced machine ...
- Copyrights in the Era of AIon February 27, 2020 at 6:06 am
Today, advancements in artificial intelligence (AI) are revolutionizing the creative process ... Generally, accessing copyrighted works for use in training algorithms does not reduce the economic ...
- Intel AI head steps down weeks after chipmaker's pivot toward Habana Labs processorson February 26, 2020 at 11:58 am
The head of Intel Corp.’s Artificial Intelligence Products Group is stepping down weeks after the Santa Clara chipmaker announced a pivot in its AI strategy. Naveen Rao joined Intel in 2016 when the ...
- Robotic piece picking gets more flexible with AI-enabled adaptive toolingon February 26, 2020 at 5:52 am
based XYZ’s piece picking system uses machine vision, but it does not rely exclusively on artificial intelligence ... annotating training data, Yu acknowledged. “Everyone needs data and observation of ...
- New AI Method Speeds Battery Designs for Electric Carson February 22, 2020 at 12:46 pm
Machine learning algorithms depend on the effective calibration of learning parameters and the model hyperparameters that guide the overall training process. However, the tuning is more of a form of ...
- AI can be an ally in cybersecurityon February 11, 2020 at 9:10 am
Widespread manipulation of the algorithms ... heuristic intrusion detection mechanisms, endpoint detection and response solutions, and more) cross swords with countless human adversaries. And ...
- Bring the Noiseon February 10, 2020 at 11:35 am
Those who design deep neural networks for artificial intelligence often find inspiration in the ... Yet, Mahmoodi notes, “You can use neural networks and heuristic algorithms to find a kind of a ...
via Bing News