As the co-founder and CEO of Affectiva, el Kaliouby is on a mission to expand what we mean by "artificial intelligence" and create intelligent machines that understand our emotions. The new AI category el Kaliouby and her team at Affectiva are spearheading is "Emotion AI," defining a new market by pursuing two goals: Allowing machines to adapt to human emotions in real-time and providing insights and analytics so organizations can understand how people engage emotionally in the digital world. Then she read Picard's Affective Computing, published in 1997, and became "super-fascinated by the idea that a computer can read people's emotions. For her dissertation, el Kaliouby used the autism research center's data to train a computer model to recognize accurately and in real-time complex mental states with "an accuracy and speed that are comparable to that of human recognition."
By training a machine learning algorithm on their behavior and earlier MRI data, the scientists built a model that predicted 9 of those 11 autism cases, with no false positives. Right now, researchers tracking autism development focus on infant siblings of people with autism; they have 1 in 5 chance of developing autism, compared to around 1 in 100 for the general population. But current autism therapies for babies and toddlers focus on their specific behavioral deficits--teaching children to communicate needs, to play with toys, and to have positive interactions with caregivers. The UNC group's next goal is to predict specific autism symptoms, correlating brain scans with future language difficulties, sensory sensitivities, social difficulties, or repetitive behaviors.
In addition to brain scan data, researchers could gather behavioral results, environmental exposures, and more. Each functional connectivity MRI (fcMRI) scan measured the activity of 26,335 brain connections among 230 brain regions. In some cases, brain connections of children diagnosed with autism were highly synchronized; in others, the connections were less synchronized. The study is the most recent of four papers resulting from the Infant Brain Imaging Study, a U.S. National Institutes of Health–funded study of early brain development in autism.
"It was extremely accurate," Robert Emerson, the lead author on the study and a former cognitive neuroscience postdoctoral fellow at the University of North Carolina (UNC), told Live Science. Studies show that 20 percent of babies who have older siblings with autism will develop the disorder; among babies in the general population, 1.5 percent develop autism, Emerson told Live Science. In this case, the program was learning to spot differences between the functional connections imaged in the MRI data collected at 6 months old that correlate with cognition, memory and behavior and the details from the behavioral assessments collected at 24 months. Piven said the team published a study earlier in the year that also showed an impressive prediction rate, but that study required two MRI scans, one at 6 months of age and one at 1 year.
Previous work has identified that bundles of nerve fibres in the brain develop differently in infants with older siblings with autism from how they do in infants without this familial risk factor. The team used the brain scans from when the babies were 6 months old and behavioural data from when the children were 2 years old to train a machine-learning program to identify any brain connectivity patterns that might be linked to later signs of autism, such as repetitive behaviour, difficulties with language, or problems relating socially to others. After the training, the program used only the patterns from the 6-month-old brains to predict which of the children would show signs of autism at 2 years old. The goal is to use such a classifier system to identify infants likely to develop autism at an early age.
Kohane shared research that found claims data more predictive than genomic tests for parents who have had a single autistic child who were looking to understand the probability of a second child having a diagnosis of autism. PathAI's CEO, Andy Beck, showed a demonstration of how his company is using machine learning to improve breast cancer diagnostics, and Harvard Medical School's, Hugo Aerts, Scientific Advisor to Sphera, showed how lung cancer detection can be improved. An impressive moment occurred when Andy Beck highlighted an image, indicating areas where the AI had higlighted areas on which the pathologist should focus, and the AI had provided some decision support suggesting the content. A great example was the AI driven drug hypothesis generation machine that Jérôme described, and then followed-up to explain how difficult it is to then determine whether a hypothesis is novel or not.
PARIS – Scientists on Monday announced the discovery of 52 genes linked to human intelligence, 40 of which have been identified as such for the first time. Taken together, the new batch of "smart genes" accounted for 20 percent of the discrepancies in IQ test results among tens of thousands of people examined, the researchers reported in the journal Nature Genetics says. Many of the genetic variations linked with high IQ also correlated with other attributes: more years spent in school, bigger head size in infancy, tallness, and even success in kicking the tobacco habit. To challenge their own results, the researchers separately checked the 13 databases they drew from -- each had used slightly different IQ tests -- against the 52 gene variants to see if the combined match-up between intelligence and genetic profile held up.
But the technology underlying Alexa can do more important things like helping people with special needs do more things on their own. The first tool, "Lex," lets programmers build speech recognition into their own software. Pollexy ("Polly" "Lex") is a Raspberry Pi and mobile-based special needs verbal assistant that lets caretakers schedule audio task prompts and messages both on a recurring schedule and/or on-demand. Lisa Yang, the co-founder of MIT's new Hock E. Tan and K. Lisa Yang Center for Autism Research, said Alexa and similar technologies like Microsoft (msft) Cortana or Google (googl) Assistant could help many people on the autism spectrum who tend to be compliant because they've had to interact with therapists for most of their lives.
The smooth, silicon instrument helps autistic kids bridge social gaps by letting them harmonize -- literally -- with playmates. Leka plays sounds and music, lights up, vibrates, and even speaks to help engage autistic children in multi-sensory activities. Creators of a new conversation coach for smartwatches want to help decipher nonverbal communication, like facial expressions and gestures, to help children with Asperger's navigate social interactions. While it was designed to facilitate music therapy, the gadget can also help bridge communication gaps between autistic and non-autistic people, giving autistic children a sensory-friendly experience that calms nerves and encourages interaction at the same time.
"This is nice, it tickles me," Kaspar the social robot tells four-year-old Finn as they play together at an autism school north of London. Kaspar, developed by the University of Hertfordshire, also sings song, imitates eating, plays the tambourine and combs his hair during their sessions aimed at helping Finn with his social interaction and communication.