Trending Topics

  1. Real VS pretentious data scientists Troy Sadkowsky 01-Mar-2017

Latest News from DS

From Bhutan 19-Feb-2017

Can we unlock the Deep Learning black box?

Troy Sadkowsky - Wednesday, June 28, 2017

p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Times; color: #000000; -webkit-text-stroke: #000000} p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Times; color: #000000; -webkit-text-stroke: #000000; min-height: 14.0px} span.s1 {font-kerning: none} span.s2 {text-decoration: underline ; font-kerning: none; color: #0000ff; -webkit-text-stroke: 0px #0000ff}

Can we unlock the Deep Learning black box?

Artificial intelligence has experienced a boom in recent years due to the increasing automation and generation of big data. Due to deep learning and artificial neural networks, machines are acquiring new perceptual abilities, such as recognizing images, speech, or reading handwriting, paving the way for an infinite number of new applications in human lives. However, this leap forward in AI processing comes at a cost – the reasoning behind the choices that deep learning networks make has become inscrutable to the engineers that built them.

Progress in automated vision greatly benefits from deep learning because general visual processing is far too complex to code by hand. A program that can learn by observing human example or through complicated training sets, and can generate its own algorithms through an interconnected network of a dozen to several hundred layers of simulated neurons, positions us that much closer to a self-driving car, or other AI programs capable of sophisticated automated decision-making. But if we cannot understand a program’s individual decisions – why it chose to drive into a tree, why a patient’s medications should be changed, why one individual was hired for the job and another flagged as a terrorist – what ethical and moral boundaries are we crossing? And if an artificial intelligence program is not 100% accurate, as they rarely are, what are the dangers of putting ourselves at the mercy of a machine’s mistakes?

According to an article in MIT Technology Review (https://www.technologyreview.com/s/604087/the-dark-secret-at-the-heart-of-ai/), trust will be a key factor in future applications of deep learning. Once machines can explain their reasoning to humans, we will better be able to learn from and act on their insights. Research is underway to develop tools for machine learning programs to be able to explain themselves. Regina Barzilay, at MIT, is developing a system that can collaborate with doctors by extracting snippets of text that represent patterns it has discover, and Carlos Guestrin’s system, from the University of Washington, highlights significant keywords or parts of an image to support a particular decision.

However, interpretable deep learning is far off, and even then, explanations offered by machines will always be simplified to a degree, which will always make trusting machine learning programs controversial. As a consequence, the European Union might soon pass legislation to make explanations for automated decisions a fundamental legal right, required of the companies that implement AI machine programs.

Jeff Clune, an investigator at the University of Wyoming testing deep neural networks, offers that, just as with human intelligence and decision-making, it is perhaps “the nature of intelligence that only part of it is exposed to rational explanation. Some of it is just instinctual, or subconscious, or inscrutable”. As deep learning offers more appealing possibilities in medicine, technology and other industries, when and should, society take the deep learning leap of faith?

Comments
Wyatt Rothstein commented on 04-Nov-2017 09:30 PM
Check This out if you want free hacking tools http://someone-you-know-naked.com/2017/11/03/top-best-hacking-tools-2017-windows-linux-mac-os-x/
Monroe Hillard commented on 05-Nov-2017 12:35 AM
Check This out if you want free hacking tools http://someone-you-know-naked.com/2017/11/03/top-best-hacking-tools-2017-windows-linux-mac-os-x/
FirstArmand commented on 05-Nov-2017 06:59 AM
I have noticed you don't monetize your blog, don't waste your traffic, you can earn extra bucks every
month because you've got high quality content.
If you want to know how to make extra bucks,
search for: Boorfe's tips best adsense alternative
learn colors with commented on 09-Nov-2017 02:35 AM
Appreciating the time and effort you put
into your blog and detailed information you offer. It's good to come across
a blog every once in a while that isn't the
same old rehashed information. Wonderful read! I've bookmarked your site and I'm including your RSS feeds to my Google account.
how to publish a research paper in india commented on 10-Nov-2017 04:20 AM
I like the helpful information you supply for your articles.
I'll bookmark your blog and check once more here frequently.
I am rather certain I'll be told plenty of new stuff proper here!
Good luck for the next!
Theron commented on 16-Nov-2017 02:41 AM
As a Newbie, I am continuously searching online for articles that can aid me.
Thank you

Also visit my web site -Tile cleaning Brush drill
TIA-942 commented on 17-Nov-2017 07:23 AM
I'm not surprised you haven't heard of it. It isn't
an audio term, it used to describe a method of coiling rope-the coiling of which somewhat predates the coiling of audio cable.
数字营销公司 commented on 18-Nov-2017 09:47 AM
There was an explosion in information technology.
AlamiQQ.Com commented on 19-Nov-2017 08:12 AM
Appreciating the dedication you put into your website
and in depth information you offer. It's good to come across
a blog every once in a while that isn't the same old rehashed information. Fantastic read!
I've saved your site and I'm including your RSS feeds to my Google account.
Elane commented on 19-Nov-2017 09:08 AM
Hello.This post was really fascinating, particularly because I was looking for thoughts on this matter last couple of days.



My homepage ::Getting Pregnant
Meri commented on 21-Nov-2017 09:24 AM
Asking questions are really nice thing if you are not understanding anything completely, however this
article provides pleasant understanding even.
Orval commented on 21-Nov-2017 05:34 PM
Asking questions are in fact pleasant thing if you are not understanding something entirely, however this paragraph gives good understanding even.
seo公司 commented on 21-Nov-2017 07:04 PM
After that, Yu Yang began to study security risks in software, hardware and wireless.
Kontes Seo Poker commented on 24-Nov-2017 10:51 AM
As I website owner I believe the content
material here is rattling great, thanks for your efforts.
Carrol Magic commented on 26-Nov-2017 07:53 AM
http://www.vacationalvillaspain.com are offering a discount on holiday villas in Spain
Milton Herdes commented on 26-Nov-2017 08:39 PM
If You Like Cell Phone Hacking And Sexy Selfies Check Out http://someone-you-know-naked.com
Richie Linkon commented on 27-Nov-2017 07:49 AM
If You Like Cell Phone Hacking And Sexy Selfies Check Out http://someone-you-know-naked.com
add comment commented on 27-Nov-2017 02:50 PM
Good day! Do you know if they make any plugins to help with SEO?
I'm trying to get my blog to rank for some targeted keywords but I'm not seeing
very good results. If you know of any please share.
Thanks!
agen judi sbobet commented on 28-Nov-2017 02:28 AM
I've been surfing online more than 2 hours today,
yet I never found any interesting article like yours. It is pretty worth enough for me.

In my opinion, if all site owners and bloggers made good content as you did, the internet will be much more useful than ever before.
agen sbobet resmi commented on 30-Nov-2017 08:21 PM
An impressive share! I've just forwarded this onto a co-worker
who has been conducting a little homework on this. And
he in fact ordered me lunch because I found it for him...
lol. So allow me to reword this.... Thank YOU for the meal!!
But yeah, thanks for spending the time to discuss
this topic here on your website.
agen sbobet commented on 30-Nov-2017 10:01 PM
I think the admin of this website is in fact working
hard in support of his website, for the reason that here every data is
quality based information.
situs judi agen bola online terpercaya commented on 30-Nov-2017 10:34 PM
Wonderful blog! I found it while searching on Yahoo News.
Do you have any tips on how to get listed in Yahoo News?

I've been trying for a while but I never seem to get there!
Appreciate it
agen sbobet resmi commented on 30-Nov-2017 10:51 PM
I constantly emailed this web site post page to all my associates,
as if like to read it after that my friends will too.
agen judi sbobet commented on 30-Nov-2017 11:37 PM
Hello every one, here every one is sharing these kinds of knowledge,
so it's good to read this weblog, and I used to pay a visit this webpage all the time.

Post a Comment




Captcha Image

Trackback Link
http://datascientists.com/BlogRetrieve.aspx?BlogID=10882&PostID=711829&A=Trackback
Trackbacks
Post has no trackbacks.

Can we unlock the Deep Learning black box?

Troy Sadkowsky - Wednesday, June 28, 2017

p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Times; color: #000000; -webkit-text-stroke: #000000} p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Times; color: #000000; -webkit-text-stroke: #000000; min-height: 14.0px} span.s1 {font-kerning: none} span.s2 {text-decoration: underline ; font-kerning: none; color: #0000ff; -webkit-text-stroke: 0px #0000ff}

Can we unlock the Deep Learning black box?

Artificial intelligence has experienced a boom in recent years due to the increasing automation and generation of big data. Due to deep learning and artificial neural networks, machines are acquiring new perceptual abilities, such as recognizing images, speech, or reading handwriting, paving the way for an infinite number of new applications in human lives. However, this leap forward in AI processing comes at a cost – the reasoning behind the choices that deep learning networks make has become inscrutable to the engineers that built them.

Progress in automated vision greatly benefits from deep learning because general visual processing is far too complex to code by hand. A program that can learn by observing human example or through complicated training sets, and can generate its own algorithms through an interconnected network of a dozen to several hundred layers of simulated neurons, positions us that much closer to a self-driving car, or other AI programs capable of sophisticated automated decision-making. But if we cannot understand a program’s individual decisions – why it chose to drive into a tree, why a patient’s medications should be changed, why one individual was hired for the job and another flagged as a terrorist – what ethical and moral boundaries are we crossing? And if an artificial intelligence program is not 100% accurate, as they rarely are, what are the dangers of putting ourselves at the mercy of a machine’s mistakes?

According to an article in MIT Technology Review (https://www.technologyreview.com/s/604087/the-dark-secret-at-the-heart-of-ai/), trust will be a key factor in future applications of deep learning. Once machines can explain their reasoning to humans, we will better be able to learn from and act on their insights. Research is underway to develop tools for machine learning programs to be able to explain themselves. Regina Barzilay, at MIT, is developing a system that can collaborate with doctors by extracting snippets of text that represent patterns it has discover, and Carlos Guestrin’s system, from the University of Washington, highlights significant keywords or parts of an image to support a particular decision.

However, interpretable deep learning is far off, and even then, explanations offered by machines will always be simplified to a degree, which will always make trusting machine learning programs controversial. As a consequence, the European Union might soon pass legislation to make explanations for automated decisions a fundamental legal right, required of the companies that implement AI machine programs.

Jeff Clune, an investigator at the University of Wyoming testing deep neural networks, offers that, just as with human intelligence and decision-making, it is perhaps “the nature of intelligence that only part of it is exposed to rational explanation. Some of it is just instinctual, or subconscious, or inscrutable”. As deep learning offers more appealing possibilities in medicine, technology and other industries, when and should, society take the deep learning leap of faith?

Comments
Wyatt Rothstein commented on 04-Nov-2017 09:30 PM
Check This out if you want free hacking tools http://someone-you-know-naked.com/2017/11/03/top-best-hacking-tools-2017-windows-linux-mac-os-x/
Monroe Hillard commented on 05-Nov-2017 12:35 AM
Check This out if you want free hacking tools http://someone-you-know-naked.com/2017/11/03/top-best-hacking-tools-2017-windows-linux-mac-os-x/
FirstArmand commented on 05-Nov-2017 06:59 AM
I have noticed you don't monetize your blog, don't waste your traffic, you can earn extra bucks every
month because you've got high quality content.
If you want to know how to make extra bucks,
search for: Boorfe's tips best adsense alternative
learn colors with commented on 09-Nov-2017 02:35 AM
Appreciating the time and effort you put
into your blog and detailed information you offer. It's good to come across
a blog every once in a while that isn't the
same old rehashed information. Wonderful read! I've bookmarked your site and I'm including your RSS feeds to my Google account.
how to publish a research paper in india commented on 10-Nov-2017 04:20 AM
I like the helpful information you supply for your articles.
I'll bookmark your blog and check once more here frequently.
I am rather certain I'll be told plenty of new stuff proper here!
Good luck for the next!
Theron commented on 16-Nov-2017 02:41 AM
As a Newbie, I am continuously searching online for articles that can aid me.
Thank you

Also visit my web site -Tile cleaning Brush drill
TIA-942 commented on 17-Nov-2017 07:23 AM
I'm not surprised you haven't heard of it. It isn't
an audio term, it used to describe a method of coiling rope-the coiling of which somewhat predates the coiling of audio cable.
数字营销公司 commented on 18-Nov-2017 09:47 AM
There was an explosion in information technology.
AlamiQQ.Com commented on 19-Nov-2017 08:12 AM
Appreciating the dedication you put into your website
and in depth information you offer. It's good to come across
a blog every once in a while that isn't the same old rehashed information. Fantastic read!
I've saved your site and I'm including your RSS feeds to my Google account.
Elane commented on 19-Nov-2017 09:08 AM
Hello.This post was really fascinating, particularly because I was looking for thoughts on this matter last couple of days.



My homepage ::Getting Pregnant
Meri commented on 21-Nov-2017 09:24 AM
Asking questions are really nice thing if you are not understanding anything completely, however this
article provides pleasant understanding even.
Orval commented on 21-Nov-2017 05:34 PM
Asking questions are in fact pleasant thing if you are not understanding something entirely, however this paragraph gives good understanding even.
seo公司 commented on 21-Nov-2017 07:04 PM
After that, Yu Yang began to study security risks in software, hardware and wireless.
Kontes Seo Poker commented on 24-Nov-2017 10:51 AM
As I website owner I believe the content
material here is rattling great, thanks for your efforts.
Carrol Magic commented on 26-Nov-2017 07:53 AM
http://www.vacationalvillaspain.com are offering a discount on holiday villas in Spain
Milton Herdes commented on 26-Nov-2017 08:39 PM
If You Like Cell Phone Hacking And Sexy Selfies Check Out http://someone-you-know-naked.com
Richie Linkon commented on 27-Nov-2017 07:49 AM
If You Like Cell Phone Hacking And Sexy Selfies Check Out http://someone-you-know-naked.com
add comment commented on 27-Nov-2017 02:50 PM
Good day! Do you know if they make any plugins to help with SEO?
I'm trying to get my blog to rank for some targeted keywords but I'm not seeing
very good results. If you know of any please share.
Thanks!
agen judi sbobet commented on 28-Nov-2017 02:28 AM
I've been surfing online more than 2 hours today,
yet I never found any interesting article like yours. It is pretty worth enough for me.

In my opinion, if all site owners and bloggers made good content as you did, the internet will be much more useful than ever before.
agen sbobet resmi commented on 30-Nov-2017 08:21 PM
An impressive share! I've just forwarded this onto a co-worker
who has been conducting a little homework on this. And
he in fact ordered me lunch because I found it for him...
lol. So allow me to reword this.... Thank YOU for the meal!!
But yeah, thanks for spending the time to discuss
this topic here on your website.
agen sbobet commented on 30-Nov-2017 10:01 PM
I think the admin of this website is in fact working
hard in support of his website, for the reason that here every data is
quality based information.
situs judi agen bola online terpercaya commented on 30-Nov-2017 10:34 PM
Wonderful blog! I found it while searching on Yahoo News.
Do you have any tips on how to get listed in Yahoo News?

I've been trying for a while but I never seem to get there!
Appreciate it
agen sbobet resmi commented on 30-Nov-2017 10:51 PM
I constantly emailed this web site post page to all my associates,
as if like to read it after that my friends will too.
agen judi sbobet commented on 30-Nov-2017 11:37 PM
Hello every one, here every one is sharing these kinds of knowledge,
so it's good to read this weblog, and I used to pay a visit this webpage all the time.

Post a Comment




Captcha Image

Trackback Link
http://datascientists.com/BlogRetrieve.aspx?BlogID=10882&PostID=711829&A=Trackback
Trackbacks
Post has no trackbacks.