Google\u2019s Geoffrey Hinton, an artificial intelligence pioneer, in November outlined an advance in the technology that improves the rate at which computers correctly identify images and with reliance on less data.
\nHinton, an academic whose previous work on artificial neural networks is considered foundational to the commercialization of machine learning, detailed the approach, known as capsule networks, in two research papers posted anonymously on academic websites last week.
\nThe approach could mean computers learn to identify a photograph of a face taken from a different angle from those it had in its bank of known images. It could also be applied to speech and video recognition.
\n\u201cThis is a much more robust way of identifying objects,\u201d Hinton told attendees at the Go North technology summit hosted by Alphabet Inc\u2019s Google, detailing proof of a thesis he had first theorized in 1979.
\nIn the work with Google researchers Sara Sabour and Nicholas Frost, individual capsules – small groups of virtual neurons – were instructed to identify parts of a larger whole and the fixed relationships between them.
\nThe system then confirmed whether those same features were present in images the system had never seen before.
\nArtificial neural networks mimic the behavior of neurons to enable computers to operate more like the human brain.
\nHinton said early testing of the technique had come up with half the errors of current image recognition techniques.
\nThe bundling of neurons working together to determine both whether a feature is present and its characteristics also means the system should require less data to make its predictions.
\n\u201cThe hope is that maybe we might require less data to learn good classifiers of objects, because they have this ability of generalizing to unseen perspectives or configurations of images,\u201d said Hugo Larochelle, who heads Google Brain\u2019s research efforts in Montreal.
\n\u201cThat\u2019s a big problem right now that machine learning and deep learning needs to address, these methods right now require a lot of data to work,\u201d he said.
\nHinton likened the advance to work two of his students developed in 2009 on speech recognition using neural networks that improved on existing technology and was incorporated into the Android operating system in 2012.
\nStill, he cautioned it was early days.
\nRead the source article at Reuters.com.
\nSource: AI Trends<\/p>\n","protected":false},"excerpt":{"rendered":"Google\u2019s Geoffrey Hinton, an artificial intelligence pioneer, in November outlined an advance in the technology that improves the…\n","protected":false},"author":1,"featured_media":3548,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[811],"tags":[812],"class_list":{"0":"post-3547","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai"},"yoast_head":"\n