I wonder what effect this will have on our culture long term. It would be unfortunate if Glass' determination ends being seen as the ground truth.
I have noticed a certain phenomenon where people who are bad at something read books about it to compensate, and then having read books on the subjects start considering themselves experts on it and preach to others, closing the loop from descriptive to prescriptive.
> I have noticed a certain phenomenon where people who are bad at something read books about it to compensate, and then having read books on the subjects start considering themselves experts on it and preach to others, closing the loop from descriptive to prescriptive.
I had a bad case of this, I did it a lot. Fortunately, some people made me aware of this tendency. Now a lot of those things I've learned are natural as if they've always been part of me. To be fair, there's 10 years in between both points.
Only a beginner can teach a beginner. First you struggle. Then you think you know it all. Then you forget what was so hard. Then you master it. And then you realize you know very little.
> I have noticed a certain phenomenon where people who are bad at something read books about it to compensate, and then having read books on the subjects start considering themselves experts on it and preach to others, closing the loop from descriptive to prescriptive.
A motivating way to learn is to teach or re-iterate what you know, you learn new things that way. Going overboard or thinking you are a genius on the topic suddenly is annoying but sometimes it is how that person is motivated.
As far as sharing what people know through learning, that they previously didn't know and is interesting and fresh to their mind, that is part of their learning process.
Spaced Learning [1] + Spaced Repetition [2] are very effective learning/memory techniques, revisiting a topic many times over time.
Even commenting on topics you are into or researched on, simply restating them sometimes leads to learning more about it, at a minimum it sets it into your knowledge through repetition or spaced learning.
There is a fun spaced learning game using Spaced Repetition called How To Remember Anything Forever-ish [3].
Really both techniques just pattern-ize already existing techniques how people learn things through repetition and time. It is really just revisiting a topic in intervals that will put it in memory and make it important, which the brain will spend more cycles on, and new ideas and uses for that knowledge come up.
Talking or sharing what you know about what you just learned is part of that unstructured spaced learning/repetition that helps learn. It plays into presentation as well, when you are teaching a topic you start by summarizing, then get to the details, then resurface with the summary while hitting key points multiple times throughout. A teacher or presenter will learn more and more the more they repeat that topic/lesson etc that is impossible to get to on early iterations or draft/sketch phases.
I think everyone to some extent learns to hack some aspect or another of the social fabric by something close to simulating patterns which come more or less natural to another person. But there are introspective lessons in coming to terms with these obstacles in the first place that are maybe the things of truer value and which could be lost in artificial reward games.
I recognize the phenomenon. I once had a roommate who changed his major to communications and then bragged that it was his life's calling and he was the best at communication. He fought with us over stupid stuff and never learned to listen. Drove us totally insane. He used to say that we were going to be bad husbands in the future because we didn't mention things that bothered us as aggressively as he did. Another friend who studied communications very seriously said that many communications professors had marital issues because of their belief in their own abilities. Totally anecdotal, of course.
It is worth noting that difficulties in recognising emotions in faces are by no means unique to ASD; they also occur in ADHD [1], anxiety disorders [2], schizophrenia [3], and probably other psychiatric/neurodevelopmental disorders as well. So, if this technology has value, its value would be a lot broader than only ASD.
(As an aside, a lot of people tend to have this narrow focus on just ASD to the exclusion of other psychiatric/neurodevelopmental disorders, despite the fact that all these disorders have lots of overlap and rather fuzzily defined boundaries. None of the symptoms of ASD are unique to ASD; they all occur in other conditions also; given that all treatments for ASD are treating symptoms rather than the unknown underlying causes, any therapy for any ASD symptom is very likely to also work for other disorders in which the same symptom is expressed.)
That makes good sense. ASD is a catch all term for those with certain symptoms that are unexplained by other factors. Schizophrenia and anxiety disorders would be some of those other factors. Not sure about ADHD.
Yeah, that was my initial reaction (though without your knowledge of the topic): there are a lot of people who could benefit from this, not just those with autism.
Such studies, papers and news always makes me cringe.
It seems overly engineered with limited usefulness.
Superpower glass … really?
As background I work in public research and have no background in Autism research.
Yet, due to a mutual friend, I was lucky to meet Kelly Hunter, and attend one of her workshops (together with several other researchers working on helping autistic children).
I knew the Stanford project, mentioned it and got just strange looks:
“This does not really solve any of the problems we are facing”
It seems detecting facial emotions are not the main problems of the autistic children they are dealing with ...
The system itself can just help children with very mild symptoms.
One colleague who works on wearable sensing for them mentioned that even head bands and wrist watches cannot be used
as children commonly take them off and throw them around.
Autism is a spectrum disorder, which means there is a wide range of afflictions, and the afflictions range from very, very mild to debilitating.
Conducting research for something that is spectrum based is frustrating because researchers can only target one small area. The approach is necessary in order to tackle the problem because the problem is so large, we'll need a lot of researchers working on a lot of very focused areas in order to move forward in a broad fashion.
It turns out that people with autism do have difficulty detecting emotions. A classic task in the lab is the "reading the mind in the eyes" task (http://socialintelligence.labinthewild.org/mite/), whereby individuals need to identify the emotion someone is expressing by looking at a picture of their eyes. People with autism consistently show lower scores than healthy controls.
Would a therapy like the one you described be better than a technology like this? Maybe. But therapy also very expensive, time consuming, and prohibitive for people who don't have time to take their kid to it every week. We are always looking for new approaches. Even if technology like this doesn't work out, learning why it doesn't work will be helpful for developing future treatments which are better. Remember that this is active research, not an established methodology. (Don't be put off by the "breakthrough therapy" designation mentioned in the article, which is a bureaucratic technical term used by the FDA.)
The paper you linked to is about monitoring, and is not useful by itself without a therapist to interpret it and evaluate it. There is not yet established methodology on how to use this kind of data.
On a related note, there has been a lot of interest recently in real-time feedback for enhanced therapy and treatment. There is a growing literature on neurofeedback in particular, such as reducing depression symptoms by training someone to control their neural activity (e.g. see https://www.youtube.com/watch?v=Xb7bgNo3sUs). Exciting stuff!
What's the point of knowing someone is angry if you do not know why he is angry? Detecting emotions doesn't strike me as particularly useful. Manipulating emotions of others on the other hand,...
It sounds to me like you could do a lot more to just educate the parents.
You don't get mad and shout at a young child who has decided to put the silverware away. You talk to them about the process of making and serving dinner. He could have been shown that one way to make the silverware more orderly is set the table for everyone while Mom cooks.
That was my response to my then five year old being impatient with dinner not being ready. I taught him he was allowed to set the table to keep himself occupied and help me get dinner ready faster.
He wasn't required to set it. He was empowered to do so if he chose rather than being a pain in the butt for me.
The example is just one example. For some parents, it's this but all the time with different things.
ASD* kids don't learn like neurotypical kids and if you treat them the same you will quickly get exhausted. As someone who has had classes on this, you can't "educate" the kid out of being autistic, and many have tried. This technology is just an adaptive tool, and a great one if it works.
Honestly seems like you just read the first two paragraphs and stopped. As a father of two autistic children, it's more than just how to speak, or even explaining things if you are lucky enough that your children are verbal. This isn't about wearing the glasses long term, it's about a tool used to teach the children social skills. About recognizing facial expressions, an issue many autistics have.
This isn't about educating parents on how to talk to their children. It's about educating autistics on how to interpret faces in different people.
> Children are expected to quickly learn how to detect the emotions of their social partners and then, after they’ve gained social confidence, stop using the glasses.
The point is that autistic people may not possess a theory of mind. They do not understand or anticipate the desires and intentions of others, and may not be aware that other people even have desires and intentions. You can't explain dinner to them if they are unable to comprehend that you intend to make it and that you desire the space and time to do so efficiently.
On one hand, I really welcome technologies like this that empower people in a huge way. On the other hand, I really dread that in this case it comes from the company that wants to know everything about you.
The example where Google hid a microphone in Nest makes me believe they will do anything to get more information from people. I think it's not beyond Google to use people's handicaps to improve the image of Google Glass. Sorry to put it like that...
Alexithymia (this inability to recognise emotion in yourself or others) is common in autistic people, but it's neither sufficient nor required for the diagnosis. (It's not even part of the diagnosis).
I mention this because autistic people often wait a long time for a diagnosis, and part of that is this idea that all autistic people are unable to recognise emotion.
I imagine that there are nuances to facial expression that might be difficult to extract from an image or video, depending on the parameters to your ML model.
For example, if someone looks into my eyes, furrows their brows, and shakes their head slowly back and forth, this could mean that they are intensely sympathetic with me (when I am talking), or it could mean that they are disgusted with what I have said (when I have stopped talking), or many other things. If you add sound input to your model then maybe it can figure out how to incorporate that dimension into its results.
Very cool though. Maybe you could have something like this to help colorblind people see colors, deaf people see sounds, the possibilities are exciting.
I assume there are potential users who can’t easily perceive furrowing of brows, but who could infer its context-dependent meaning if it were made more obvious when it’s happening.
I've wanted something exactly like this, i can read emotions when iam putting close effort into the activity however it's exhausting to do so, reducing the mental toll on myself and other in social interaction is appreciated. Less meltdowns and misunderstandings would a upgrade.
while it sounds too good to be true at this moment i worry that the black box that tells the user the emotion gives no feedback to why it did so, transparently to the user to make a good judgement is essential.
this becomes the heading aid to the autistic it will be same problem the hearing impaired deal with then people find issue with the different.
Although it may be creepy from the perspective of privacy, for those who are okay with it, I imagine that children struggling with Theory of Mind performance might benefit from recording their everyday experiences, and then later having a trusted therapist offer guiding opinion. Google Glass seems to be amenable to something like that.
Sounds great on paper but I highly disagree with the universality of emotions and their represented facial clues. How Emotions Are Made by Lisa Barrett goes into great lengths about this. I think taking this technology into a categorization of emotions is faulty at best and dangerous at worst.
I could use this. Never been tested for Aspergers but could never flex that muscle everyone else seems to have where they can “read the room”. Wife swears I’m on the spectrum. This would save me from many future difficult situations.
Some good info written in annoying marketing press release style. Would be good to get this as a phone app with a headmounted camera, since that's far cheaper than Google Glass + doctor's prescription.
> The glasses are not meant to be a permanent prosthesis. The kids do 20-minute sessions a few times a week in their own homes, and the entire intervention currently lasts for six weeks. Children are expected to quickly learn how to detect the emotions of their social partners and then, after they’ve gained social confidence, stop using the glasses.
Cultural differences will be one of the difficulties for this idea to be successful. Eg, I know that some cultural, they smile when scared. You can see where this might lead to the wrong conclusion.
This is awful. Autistic kids don't need to change how they view emotions. Other people need to be more accepting that other people may not care about their emotions as much as they do.
If this works effectively I think it's a valuable choice to offer to autistic people - whether they choose to use it or not is totally valid of course. Often what people with disabilities are forced to do is choose an imperfect "accommodation", or choose to not participate in something at all, since it is not an option to instantly convert our society to a more compassionate, understanding, and fair place.
I agree with you that the real thing here is that we should accept all people regardless of how they view/prioritize our emotions and meet each other where we all are. But until we are all in that same agreement, I'm all for tools that provide increased agency/information to people who want to use those tools.
I wonder about the opposite application - using it to read autistic emotional signs. Outbursts have ample build up and signs but they aren't noticed or are misread. Because autistic tells aren't neccessarily the same. I liken the situation to trying to treat a cat like a dog and then wondering why they claw you after wagging its tail - in cats that doesn't mean "happy" it means "back off!". Communication is fundamentally a two way street.
This is pretty cool. I didn't really get to do this sorta thing with a speech therapist until I was in middle school. I think it'd be pretty good for young children.
One small worry... I wouldn't want the child to get overdependent on the device. Perhaps it would be good if they only wear it for a certain portion of the day? Not sure.
[+] [-] im3w1l|6 years ago|reply
I have noticed a certain phenomenon where people who are bad at something read books about it to compensate, and then having read books on the subjects start considering themselves experts on it and preach to others, closing the loop from descriptive to prescriptive.
Edited: Added second paragraph
[+] [-] mettamage|6 years ago|reply
I had a bad case of this, I did it a lot. Fortunately, some people made me aware of this tendency. Now a lot of those things I've learned are natural as if they've always been part of me. To be fair, there's 10 years in between both points.
[+] [-] z3t4|6 years ago|reply
[+] [-] drawkbox|6 years ago|reply
A motivating way to learn is to teach or re-iterate what you know, you learn new things that way. Going overboard or thinking you are a genius on the topic suddenly is annoying but sometimes it is how that person is motivated.
As far as sharing what people know through learning, that they previously didn't know and is interesting and fresh to their mind, that is part of their learning process.
Spaced Learning [1] + Spaced Repetition [2] are very effective learning/memory techniques, revisiting a topic many times over time.
Even commenting on topics you are into or researched on, simply restating them sometimes leads to learning more about it, at a minimum it sets it into your knowledge through repetition or spaced learning.
There is a fun spaced learning game using Spaced Repetition called How To Remember Anything Forever-ish [3].
Really both techniques just pattern-ize already existing techniques how people learn things through repetition and time. It is really just revisiting a topic in intervals that will put it in memory and make it important, which the brain will spend more cycles on, and new ideas and uses for that knowledge come up.
Talking or sharing what you know about what you just learned is part of that unstructured spaced learning/repetition that helps learn. It plays into presentation as well, when you are teaching a topic you start by summarizing, then get to the details, then resurface with the summary while hitting key points multiple times throughout. A teacher or presenter will learn more and more the more they repeat that topic/lesson etc that is impossible to get to on early iterations or draft/sketch phases.
[1] https://en.wikipedia.org/wiki/Spaced_learning
[2] https://en.wikipedia.org/wiki/Spaced_repetition
[3] https://ncase.me/remember/
[+] [-] 0x8BADF00D|6 years ago|reply
[+] [-] arketyp|6 years ago|reply
[+] [-] garfieldnate|6 years ago|reply
[+] [-] skissane|6 years ago|reply
(As an aside, a lot of people tend to have this narrow focus on just ASD to the exclusion of other psychiatric/neurodevelopmental disorders, despite the fact that all these disorders have lots of overlap and rather fuzzily defined boundaries. None of the symptoms of ASD are unique to ASD; they all occur in other conditions also; given that all treatments for ASD are treating symptoms rather than the unknown underlying causes, any therapy for any ASD symptom is very likely to also work for other disorders in which the same symptom is expressed.)
[1] https://www.researchgate.net/profile/David_Da_Fonseca/public...
[2] https://www.researchgate.net/profile/Christopher_Monk2/publi...
[3] https://www.sciencedirect.com/science/article/abs/pii/S00063...
[+] [-] timwaagh|6 years ago|reply
[+] [-] SilasX|6 years ago|reply
[+] [-] kgarten|6 years ago|reply
Superpower glass … really?
As background I work in public research and have no background in Autism research. Yet, due to a mutual friend, I was lucky to meet Kelly Hunter, and attend one of her workshops (together with several other researchers working on helping autistic children). I knew the Stanford project, mentioned it and got just strange looks: “This does not really solve any of the problems we are facing” It seems detecting facial emotions are not the main problems of the autistic children they are dealing with ...
https://flutetheatre.co.uk/changing-lives-of-people-with-aut...
Here’s work from a friend on the topic: https://www.ucl.ac.uk/grand-challenges/sites/grand-challenge...
The system itself can just help children with very mild symptoms. One colleague who works on wearable sensing for them mentioned that even head bands and wrist watches cannot be used as children commonly take them off and throw them around.
Kelly also runs a fundraiser right now in case somebody wants to help out. In my personal opinion much more useful than the solution described in the ieee article: https://www.facebook.com/donate/574661226469627/101582037614...
[+] [-] watertom|6 years ago|reply
Conducting research for something that is spectrum based is frustrating because researchers can only target one small area. The approach is necessary in order to tackle the problem because the problem is so large, we'll need a lot of researchers working on a lot of very focused areas in order to move forward in a broad fashion.
[+] [-] trombonechamp|6 years ago|reply
Will improving the ability to detect emotions improve clinical outcomes? We don't know, but their initial evidence looks promising: take a look at the JAMA Pediatrics paper (https://jamanetwork.com/journals/jamapediatrics/fullarticle/...) and the Nature Digital Medicine paper (https://www.nature.com/articles/s41746-018-0035-3), which are both linked to in the article:
Would a therapy like the one you described be better than a technology like this? Maybe. But therapy also very expensive, time consuming, and prohibitive for people who don't have time to take their kid to it every week. We are always looking for new approaches. Even if technology like this doesn't work out, learning why it doesn't work will be helpful for developing future treatments which are better. Remember that this is active research, not an established methodology. (Don't be put off by the "breakthrough therapy" designation mentioned in the article, which is a bureaucratic technical term used by the FDA.)
The paper you linked to is about monitoring, and is not useful by itself without a therapist to interpret it and evaluate it. There is not yet established methodology on how to use this kind of data.
On a related note, there has been a lot of interest recently in real-time feedback for enhanced therapy and treatment. There is a growing literature on neurofeedback in particular, such as reducing depression symptoms by training someone to control their neural activity (e.g. see https://www.youtube.com/watch?v=Xb7bgNo3sUs). Exciting stuff!
[+] [-] Kaiyou|6 years ago|reply
[+] [-] DoreenMichele|6 years ago|reply
You don't get mad and shout at a young child who has decided to put the silverware away. You talk to them about the process of making and serving dinner. He could have been shown that one way to make the silverware more orderly is set the table for everyone while Mom cooks.
That was my response to my then five year old being impatient with dinner not being ready. I taught him he was allowed to set the table to keep himself occupied and help me get dinner ready faster.
He wasn't required to set it. He was empowered to do so if he chose rather than being a pain in the butt for me.
[+] [-] MagnumPIG|6 years ago|reply
ASD* kids don't learn like neurotypical kids and if you treat them the same you will quickly get exhausted. As someone who has had classes on this, you can't "educate" the kid out of being autistic, and many have tried. This technology is just an adaptive tool, and a great one if it works.
[+] [-] jasonlotito|6 years ago|reply
This isn't about educating parents on how to talk to their children. It's about educating autistics on how to interpret faces in different people.
> Children are expected to quickly learn how to detect the emotions of their social partners and then, after they’ve gained social confidence, stop using the glasses.
[+] [-] scarejunba|6 years ago|reply
[+] [-] thedance|6 years ago|reply
[+] [-] thsealienbstrds|6 years ago|reply
The example where Google hid a microphone in Nest makes me believe they will do anything to get more information from people. I think it's not beyond Google to use people's handicaps to improve the image of Google Glass. Sorry to put it like that...
[+] [-] DanBC|6 years ago|reply
I mention this because autistic people often wait a long time for a diagnosis, and part of that is this idea that all autistic people are unable to recognise emotion.
https://www.sciencedirect.com/science/article/pii/S092493381...
[+] [-] tines|6 years ago|reply
For example, if someone looks into my eyes, furrows their brows, and shakes their head slowly back and forth, this could mean that they are intensely sympathetic with me (when I am talking), or it could mean that they are disgusted with what I have said (when I have stopped talking), or many other things. If you add sound input to your model then maybe it can figure out how to incorporate that dimension into its results.
Very cool though. Maybe you could have something like this to help colorblind people see colors, deaf people see sounds, the possibilities are exciting.
[+] [-] goodside|6 years ago|reply
[+] [-] freekengeeker|6 years ago|reply
[+] [-] thomasfl|6 years ago|reply
[+] [-] threatofrain|6 years ago|reply
[+] [-] TheEndless3|6 years ago|reply
[+] [-] ryanmarsh|6 years ago|reply
[+] [-] gowld|6 years ago|reply
[+] [-] jasonlotito|6 years ago|reply
[+] [-] yitchelle|6 years ago|reply
[+] [-] tathougies|6 years ago|reply
[+] [-] doinathing|6 years ago|reply
I agree with you that the real thing here is that we should accept all people regardless of how they view/prioritize our emotions and meet each other where we all are. But until we are all in that same agreement, I'm all for tools that provide increased agency/information to people who want to use those tools.
[+] [-] Nasrudith|6 years ago|reply
[+] [-] dr_dshiv|6 years ago|reply
https://www.letsenvision.com/glasses
[+] [-] miedpo|6 years ago|reply
One small worry... I wouldn't want the child to get overdependent on the device. Perhaps it would be good if they only wear it for a certain portion of the day? Not sure.
[+] [-] nrthrn|6 years ago|reply
[+] [-] briefcomment|6 years ago|reply
[+] [-] saagarjha|6 years ago|reply