4 Burst results for "Warren Mcculloch"

"warren mcculloch" Discussed on Talking Machines

Talking Machines

12:19 min | 9 months ago

"warren mcculloch" Discussed on Talking Machines

"You are listening to talking machines Catherine Gorman Lawrence and Neil. We are again taping an episode in front of a live audience digitally recorded though on on talking machines. And if you want to be part of our live. Studio audience big quotes. You can follow us on twitter at Ti Okay. N. G. M. C. H. S. Or hit us up on the talking machines at gmail.com and our guest today for this interview on talking. Machines is Dr Terence. Annouce key doctors and thank you so much for taking the time to join us today. I really appreciate it Great to be here so we ask all of our guests the same question I. How did you get where you are? What's been your academic and industrial journey. You're also very involved in the reps conference. Tell US everything well. A wise man once told me that careers are only made retrospectively and I have no idea how he got here. There was no plan. It went through a sequence of stages starting with graduate school at Princeton in theoretical physics. From there when I finished that I for reasons that have to do with the field of physics. At the time which was a little bit more bummed I went into neuroscience so that was a post doc and then from there that's when I met. Geoffrey Hinton and had changed my life because we met him at a small seminar here in San Diego and set nineteen seventy nine. We hit it off and From that over the next few years you know blossoms the the Boehner Sheen and back prop and you know. The rest was history. Terry who you post talking with where you post talking in San Diego no no. This was a post doc at Harvard. Medical School in the Department of Neurobiology with Stephen Kofler who was widely considered to be the founder of modern neurobiology and It was an experimental post. Doc I actually recorded from neurons. Subic seventy nine. You mentioning physics. It was a little bit more bond a in some sort of connection modeling. That was also a very quiet period. That wasn't a lot going on it. Was this sort of age of classical. Ai Right you're absolutely right. This was in fact. It was the neural network winter. The seventies and it was primarily because of the failure of the perception. That's neat because you say failure of the percents on I read about that a lot. Do you really did fail. All was the men's ski paper little. What the mid ski books are in Minsk. Eighty books have killed it but was it a fair representation. Well you know it's interesting. I think that that's the myth that that book killed it but I actually think that there are other things going on and and Rosenblatt had died as well which seems pretty significant. Yes well He. He was a pioneer. But you have to understand that digital computers were regally primitive back. Then you know that even the most expensive you know the biggest computers you could buy. Don't have the power of your wristwatch today. Rosenblatt actually had to build an analog device. It a million dollars in today's dollars to build a analog device that had potentially otters driven by motors for the weight sums the learning. Wasn't it potentially because you know digital computers? Were good at logic but they were terrible. Doing a floating point is amazing so he built that at Cornell. Right that's right yeah Funded by the owner. Any case by by the time that we were getting started computers was the vaccine era. It was becoming possible. Do Simulations You know they were small-scale by today's standards but but really meant we could explorer in a way that Frank Rosenblatt couldn't so what you're saying around the perceptual and so just forbid of context for Central and sixty one. Is that right? It was fifty nine. I think it was the book but you know it was in that era of early sixty zero and so then there's this period where the digital computer actually wasn't powerful enough to do much and then digital kind of overtook and divinity but these analog machines would just now impractical from a point of view of expense. So you're saying it's less the book and more of a shift to the Digital Machine. That in those early days wasn't powerful enough to simulate the perception. Yes so I I have you know. I have a feeling that history will show that A. I was like the blind man looking under the Lamppost. His keys and someone came along and said where did you lose your keys He said well somewhere else. But this is the only place right can see. I was reading Donald BACI quote. I recently At the beginning of his book about the I which is just a fascinating area and I guess he spent a lot of his career and he did work in in the wool on radar and he was talking about the Radio Club. Which is these early Cybernet assist and the potential of the analog or digital computer to be what represented the brain and his perspective was he. He was sure it wasn't a digital computer and he wasn't sure it was an analog computer either and he thought it was kind of somewhere in between but it feels like that in between is what you're saying is that was the difficult bit to look and perhaps a police were able to look now. That's right I you know. It's I think it's being driven. This is true all science that what you cannot understand is is really determined by the tools that you have for making measurements for doing simulations in it's really only this modern era that has given us enough tools both to make progress with understanding how the brain works and also with a because of the fact that we have a tremendous amount of power now but just to go back to that early era. I think you know I once asked L. Annual you know who is at Carnegie Mellon and it was a time when Geoff Hinton was an assistant professor and I was at Johns Hopkins and I you know he was at the first fifty six meeting at Dartmouth or a I was born and I I said well. Why was it that you didn't look at the brain and for for inspiration and he said well we did. But there wasn't very much known about the at the time to help us out so we just had make doing our own and he's right. That was a era. You know the the fifties was kind of the the beginning of what we now understand about the signals in the brain. Actually potential synoptic potentials. So you know in a sense. What what he was saying was that we basically use the tools we have available the time which was basically computers but what they were good at. What were they good at? They were good at logic at rules. A binary programming. So that you know that was In a sense they were forced to do that. That's a really. WanNa come back to nine hundred seventy nine in a moment but this is an interesting context to that because of course. Vena initially was someone who spread across. Both these areas of Norbert Vena who was at mit founded cybernetics spread across both these areas of the analog and digital he did his PhD thesis on Russell and Whitehead's book but one thing I was reading about recently is there was a big falling out between Vina. I'm McCulloch Pitts. And it's sort of interesting. That Vena wasn't there at the I. E. T. in fifty six and I sometimes wonder was that more about personalities and wanting this sort of old guard to stay away because you always feel veto with someone who who bridge these worlds it. You know that's the fascinating story. I actually wrote a review of a book about Warren McCulloch came up. They were friends. They actually had had been friends yet. It has something to do with their wife's. Yeah I think the lifestyle McCullough was not line with its a side story but but I guess the point you're making which I think is an I'd like us to take us back to seventy nine and the meeting with Jeff is and I think that that's true. Despite the story between humans the real factor that drove things then was the sudden available at a t of increasing cheap digital computer. And no longer the need to do this work that Rosenblatt and McCain and others had done having to wire together a bunch of analog circuits. That you couldn't reprogram to build system. Yeah I think that was a dead. End It for the very reason you gave. Which is that you know you. It's a special purpose device. That isn't good for anything else. And and really if you're trying to explore you need the flexibility of being able to try many ideas and that's in that really is a digital simulation allows you to do you see with Aaron seventy nine so by the time. What was the picture like? In this era in seventy nine that seems like a critical period. You had the facts. You had personal machines now in effect all personal ish machines so the interesting story. My first job was at Johns Hopkins University and I was Lucky. Enough to be awarded. The Presidential Science Award Young Investigator Award from you know the the government and along with that was a grant basically and was also matching so I had to get matching funds but because of that I was able to purchase ridge computers to enrich computers which had the power of VAC seven eighties. Ulta myself and for a while had more power competing power. Thenia Tire Computer Science Department. Google of one thousand nine hundred seventy nine. That's that's right but it really. You needed it because we were doing round the clock simulations that was the era of net. Talk which made a big splash and was tell us about net talk. Because it's it's a I I know what an inspiration to people who were an inspiration to me so tell us more about net dot net tool. Well it arose from a visit I made to Princeton and a graduate student. Charlie Rosenberg. Who was working with George Miller? Who's a very eminent cognitive scientists language area and and so Charlie was really enthusiastic about neural networks. And he asks he cannot come do a summer project site. Sure and you know he was studying language. So he's he wanted to do a language network and you know we cast around for a problem. You know a small network might be able to make some progress on what were the architectures of what year is this and what were the architects is available. It was eighty five. I think summer of eighty five and it was. You know at that. Time is really interesting because when I visited Princeton we were doing bonus jeans but by the time that he showed up. Jeff had with Dave Rummelhart had just broken through with backdrop which was an order of magnitude. Faster meant we could simulate a much bigger network. Well the problem we picked out was in phonology which is how do you pronounce words. And we we. I remember going to the library. And there was a two hundred and fifty page book with filled with rules and exceptions to the rules and rules for the exceptions because English is a very irregular language and there are a lot of different influences and that notion was kind of driven by logic that was the approach to language. Let's break language down into its which was the flavor of the decade double decade. Yeah no that was the era of Chomsky and Syntax. It was clear that you know. Rule based descriptions of something regular English was really complex and I actually remember Jeff visiting during the summer and telling us. We're crazy that this is much too difficult a problem. It's a real role problem and that we should MRIs pronounciation. So we're going to build a neural network to look it. Tax Restaurant pronounced text to speech text. Which is the problem is it. The world's first text to speech system no In fact there were systems. That are out there. We bought deck talk actually which allowed us to actually hear the output of talk which made it can't come alive.

Frank Rosenblatt Princeton Jeff Geoffrey Hinton Norbert Vena San Diego twitter Catherine Gorman Lawrence Charlie Rosenberg Dr Terence Subic N. G. M. C. H. S. Harvard Minsk Warren McCulloch Thenia Tire Computer Science D Johns Hopkins University Boehner Sheen
The Evolution of ML  and Furry Little Animals

Talking Machines

08:58 min | 9 months ago

The Evolution of ML and Furry Little Animals

"You are listening to talking machines Catherine Gorman Lawrence and Neil. We are again taping an episode in front of a live audience digitally recorded though on on talking machines. And if you want to be part of our live. Studio audience big quotes. You can follow us on twitter at Ti Okay. N. G. M. C. H. S. Or hit us up on the talking machines at gmail.com and our guest today for this interview on talking. Machines is Dr Terence. Annouce key doctors and thank you so much for taking the time to join us today. I really appreciate it Great to be here so we ask all of our guests the same question I. How did you get where you are? What's been your academic and industrial journey. You're also very involved in the reps conference. Tell US everything well. A wise man once told me that careers are only made retrospectively and I have no idea how he got here. There was no plan. It went through a sequence of stages starting with graduate school at Princeton in theoretical physics. From there when I finished that I for reasons that have to do with the field of physics. At the time which was a little bit more bummed I went into neuroscience so that was a post doc and then from there that's when I met. Geoffrey Hinton and had changed my life because we met him at a small seminar here in San Diego and set nineteen seventy nine. We hit it off and From that over the next few years you know blossoms the the Boehner Sheen and back prop and you know. The rest was history. Terry who you post talking with where you post talking in San Diego no no. This was a post doc at Harvard. Medical School in the Department of Neurobiology with Stephen Kofler who was widely considered to be the founder of modern neurobiology and It was an experimental post. Doc I actually recorded from neurons. Subic seventy nine. You mentioning physics. It was a little bit more bond a in some sort of connection modeling. That was also a very quiet period. That wasn't a lot going on it. Was this sort of age of classical. Ai Right you're absolutely right. This was in fact. It was the neural network winter. The seventies and it was primarily because of the failure of the perception. That's neat because you say failure of the percents on I read about that a lot. Do you really did fail. All was the men's ski paper little. What the mid ski books are in Minsk. Eighty books have killed it but was it a fair representation. Well you know it's interesting. I think that that's the myth that that book killed it but I actually think that there are other things going on and and Rosenblatt had died as well which seems pretty significant. Yes well He. He was a pioneer. But you have to understand that digital computers were regally primitive back. Then you know that even the most expensive you know the biggest computers you could buy. Don't have the power of your wristwatch today. Rosenblatt actually had to build an analog device. It a million dollars in today's dollars to build a analog device that had potentially otters driven by motors for the weight sums the learning. Wasn't it potentially because you know digital computers? Were good at logic but they were terrible. Doing a floating point is amazing so he built that at Cornell. Right that's right yeah Funded by the owner. Any case by by the time that we were getting started computers was the vaccine era. It was becoming possible. Do Simulations You know they were small-scale by today's standards but but really meant we could explorer in a way that Frank Rosenblatt couldn't so what you're saying around the perceptual and so just forbid of context for Central and sixty one. Is that right? It was fifty nine. I think it was the book but you know it was in that era of early sixty zero and so then there's this period where the digital computer actually wasn't powerful enough to do much and then digital kind of overtook and divinity but these analog machines would just now impractical from a point of view of expense. So you're saying it's less the book and more of a shift to the Digital Machine. That in those early days wasn't powerful enough to simulate the perception. Yes so I I have you know. I have a feeling that history will show that A. I was like the blind man looking under the Lamppost. His keys and someone came along and said where did you lose your keys He said well somewhere else. But this is the only place right can see. I was reading Donald BACI quote. I recently At the beginning of his book about the I which is just a fascinating area and I guess he spent a lot of his career and he did work in in the wool on radar and he was talking about the Radio Club. Which is these early Cybernet assist and the potential of the analog or digital computer to be what represented the brain and his perspective was he. He was sure it wasn't a digital computer and he wasn't sure it was an analog computer either and he thought it was kind of somewhere in between but it feels like that in between is what you're saying is that was the difficult bit to look and perhaps a police were able to look now. That's right I you know. It's I think it's being driven. This is true all science that what you cannot understand is is really determined by the tools that you have for making measurements for doing simulations in it's really only this modern era that has given us enough tools both to make progress with understanding how the brain works and also with a because of the fact that we have a tremendous amount of power now but just to go back to that early era. I think you know I once asked L. Annual you know who is at Carnegie Mellon and it was a time when Geoff Hinton was an assistant professor and I was at Johns Hopkins and I you know he was at the first fifty six meeting at Dartmouth or a I was born and I I said well. Why was it that you didn't look at the brain and for for inspiration and he said well we did. But there wasn't very much known about the at the time to help us out so we just had make doing our own and he's right. That was a era. You know the the fifties was kind of the the beginning of what we now understand about the signals in the brain. Actually potential synoptic potentials. So you know in a sense. What what he was saying was that we basically use the tools we have available the time which was basically computers but what they were good at. What were they good at? They were good at logic at rules. A binary programming. So that you know that was In a sense they were forced to do that. That's a really. WanNa come back to nine hundred seventy nine in a moment but this is an interesting context to that because of course. Vena initially was someone who spread across. Both these areas of Norbert Vena who was at mit founded cybernetics spread across both these areas of the analog and digital he did his PhD thesis on Russell and Whitehead's book but one thing I was reading about recently is there was a big falling out between Vina. I'm McCulloch Pitts. And it's sort of interesting. That Vena wasn't there at the I. E. T. in fifty six and I sometimes wonder was that more about personalities and wanting this sort of old guard to stay away because you always feel veto with someone who who bridge these worlds it. You know that's the fascinating story. I actually wrote a review of a book about Warren McCulloch came up. They were friends. They actually had had been friends yet. It has something to do with their wife's. Yeah I think the lifestyle McCullough was not line with its a side story but but I guess the point you're making which I think is an I'd like us to take us back to seventy nine and the meeting with Jeff is and I think that that's true. Despite the story between humans the real factor that drove things then was the sudden available at a t of increasing cheap digital computer. And no longer the need to do this work that Rosenblatt and McCain and others had done having to wire together a bunch of analog circuits. That you couldn't reprogram to build system. Yeah I think that was a dead. End It for the very reason you gave. Which is that you know you. It's a special purpose device. That isn't good for anything else. And and really if you're trying to explore you need the flexibility of being able to try many ideas and that's in that really is a digital simulation allows you to

Frank Rosenblatt Geoffrey Hinton San Diego Norbert Vena Twitter Catherine Gorman Lawrence Dr Terence Subic N. G. M. C. H. S. Harvard Minsk Boehner Sheen Warren Mcculloch Princeton Cornell Donald Baci Terry Mcculloch Pitts
"warren mcculloch" Discussed on Brain Science with Ginger Campbell, MD: Neuroscience for Everyone

Brain Science with Ginger Campbell, MD: Neuroscience for Everyone

04:04 min | 1 year ago

"warren mcculloch" Discussed on Brain Science with Ginger Campbell, MD: Neuroscience for Everyone

"So let's talk a little bit about this whole AI neuro science thing, let's start out with well. How do they inform each other or fail to inform? Each other. Do you wanna start with just maybe giving us a primer of some of the important terms and principles that we need to be able to even talk about artificial intelligence that would take a week, I suppose, but if somebody's coming to your show, what kind of terms do you sort of assume they already understand. It's a changing assumption. Right. Because in the early days of the show, I would define all the terms. And I've I've found myself leaving that a lot of it to the audience assuming that they're coming in with some of this knowledge. A lot of what we talk about on the show is deep learning gladly because there has been this recent just explosion in deep learning in all sorts of industry and in neuro science. So a lot of my guests on the. Show and we explore other topics as well. But a lot of the guests on the show are exploring the the relationship between deep learning and neuroscience, and what they can gain from each other essentially, so this is a heavy topic on the show. I could give you sort of a deep learning background in the story of how that came to be if you'd like that would be a good place to start if we get a basic concept of deep learning, and then maybe we could talk about where deep learning fits into the bigger picture beautiful. Okay. So this is going to be a very abridged version of the sort of the history of depleting. And and just what it is what it means. But there's a really good book that I recommend to your listeners, and I interviewed Terry Santo ski who wrote this book called the deep learning revolution. And it really lays out the story of how we got to this point in deep learning from its founding ones, and Terri knows this stuff because he was involved in like so many steps along the way and. So many people involved in it were either from his lab or if he collaborated with them, so and it really lays this story out. Well, so I just wanted to recommend that book to your listeners. Yeah. That's on. My I wish I had time to read it list. I haven't gotten around to well, it's well written in tears, a good teacher too. So anyway, I'll send you a copy and make in guilt you into reading it. Okay. And I'll put links to it in my show notes for sure great. So just to set the context and give a little bit of background before really dive into deep learning in nineteen fifty six the term artificial intelligence rather was coined by John McCarthy during the summer conference at Dartmouth College, and this would become the famous conference called the Dartmouth College summer AI conference. This is after Walter Pitts and Warren McCulloch developed what came to be known as a McCulloch Pitts neurons, which basically is the precursor to the artificial neuron units that are used in deeply. Earning networks these days. It was also after Alan turing set the stage for computers, as we know them and machine learning as we know it, but at this time when this conference happened, most engineering and computer based solutions to solving intelligence problems were based on logical steps and manipulating symbols that humans would manually build in to the systems. Now, really where I wanna start is with what's called the perception. And I wanna start here because basically perception is deep learning without the deep part. So if we understand a perception will it's really easy to understand the deep part of the learning of you could call it. Shallow learning, I suppose, everything that's not deep learning is shallow running. Okay. So Frank Rosenblatt invented the perception in nineteen fifty seven and basically this is right. When you were being conceived. Ginger. No, I was born in nineteen fifty five fifty five. So you are maybe almost on the swing sets by this point. Not that precocious..

Dartmouth College Walter Pitts Frank Rosenblatt Terry Santo Warren McCulloch Terri John McCarthy
"warren mcculloch" Discussed on Learning Machines 101

Learning Machines 101

11:25 min | 2 years ago

"warren mcculloch" Discussed on Learning Machines 101

"On that move sequence. There. We will stop no matter what after looking ahead for about eleven news. Even if all eleven checkerboard situations. Look pretty good to us using the board evaluation row. This type of strategy is very computational tractable, and is of taking the learning machine centuries to make it a decision the learning machine can make a decision within a reasonable amount of time such as a few seconds or even a fraction of a second. So now, we haven't method that the learning machine can use to make decisions about current situations whose outcomes are not apparent until the distant future. However, we still have the final piece of the puzzle. Which is how do we combine the board features in such a way to come up with a good rating? This is where the learning by experience aspect of the checkerboard playing learning machine comes into play ideas. Very simple suppose, the machine is looking ahead on a particular move sequence six minutes into the future and the rating of the checkerboard situation. Six moves into the future is very good separate samples a rating was four this means that we would like the board evaluation roller. Tell us that the current checkerboard situation should also have a rating of four since if we make the best possible moves and the Ponant makes the best possible news that we would end up six moves into the future with a checkerboard situation rating. He put a four, however, if the current checkerboard situation as a rating of three we need to adjust the calculations associated with evaluation role. So that when the. She encounters the current checkerboard situation in the future them. She is more likely to assign a rating of four rather than three. This type of learning is related to an approach called temporal reinforcement learning because the information regarding the performance of learning machine is not provide immediately, but only provided in the future the principles and allying. This checkerboard learning machine problem are fundamentally important ideas that are central to many modern approaches to artificial intelligence than the twenty first century, they continue to be widely used in rake throughs in machine learning and artificial intelligence, which you hear about every day on the news. So to summarize these key ideas are one the concept of considering every possible sequence into the future. But using an evaluation road to eliminate exploring movie Lucy quences, which are not likely to lead to get solutions. This is called best first search in the artificial intelligence literature and to the use of an evaluation. Role for not only deciding which moves sequences are worth exploring. But also to decide which checkerboard situations are good. I e winning situations which are bad that is losing situations. Then portent of Peter's per representing the central conceptual components of prominent artificial intelligence emphasizing some aspects of the problem, which are particularly important and de emphasizing other aspects and four a learning role which compares the difference between the predictions of evaluation real and the actual observed outcomes. And then uses this discrepancy to make small adjustments to the evaluation role mechanism. It's important to note that the methods in which this learning machine uses to play checkers are not entirely human like, so for example, a computer can look ahead eleven moves into the future and thefts consider millions of possible board positions. But this is something that humans cannot ease. Easily do without additional tolls on the other hand the learning procedure used by the machine can be shown to be consistent with modern theories of biological and behavioral learning in humans the show notes at WW learning machines went to win dot com. Provides some helpful references to this literature. Your laptop computers infinitely more powerful than the computers. They used in the nineteen fifties. And yet the key principles of artificial intelligence which were implemented in this checker playing program using nineteen fifties, computer technology are still widely used today. Moreover aspects of this technology are now providing narrow scientists with guidance regarding what types of neural mechanisms might be the basis for biological human, learning and biological human intelligence. They are distantly providing Mathematica psychologists with guidance in the development of mathematical theories of human behavior and finally note that the checker playing learning machine is essentially learning at collection of roles such as in this situation, I should move. My checker piece in this particular manner. Then the next few podcasts, we will look more closely at the idea of a knowledge representation using logical roles. So this concludes the remix of episode two. Learning machines went went series before ending this podcast. However, I would like to share with you an overview of the book, the quest for artificial intelligence a history of ideas and chief mounts by professor Neal's Nelson. Professor venture nearing America's in the department of pure science at Stanford University like any other decent learning machine. I'm a firm believer that in order to predict the future. We need to understand the past the quest for artificial intelligence, a history of ideas, and achievements provides a historic on educational overview of progress in the field of artificial intelligence the end of the twentieth century, the author of the quest for artificial intelligence. His professor Nels Nelson, professor of engineering America's in the department of computer sciences, Stanford University he received his doctorate intellectually nearing from Stanford in nineteen fifty eight when the field of artificial intelligence was just in its infancy. Professor Nelson is a past president. And fellow of the sociation for the advancement of artificial intelligence and is a recognized leader in the field chapter. Went begins with early speculations about artificial intelligence by the Greek philosopher Aristotle and the talian inventor Leonardo da Vinci in the fifteenth century. Chapter two introduces the concept of Olic logic. Historical perspective by hewing contributions from the mathematician lead since in eighteenth century as well as artificial neural network architectures implementing the Bouillon logic. George bull eighteen fifty four which were described in nineteen forty three by the computational, neuroscientist or mechanic, and the brilliant young mathematician. Walter Pitts chapter three provides a fascinating review of three early and influential meetings, which signalled the fischel birth of the field of artificial intelligence. These conferences were the sessions on learning machines held at the nineteen fifty five western joint computer conference in LA the summer research project artificial intelligence at Dartmouth College in nineteen fifty six and in nineteen fifty eight a meeting titled the mechanization of thought processes located in the. United Kingdom the book continues with an evolutionary perspective on the development of artificial intelligence with some discussion of machine learning and probabilistic methods, but primarily emphasizing symbolic logic perspectives. The book ends with the review of the DARPA defense advanced research projects agency grand challenge, which was held on July thirtieth thousand to the darker challenge invited researchers from the United States design and build a driverless car capable of completing a one hundred forty two mile course, from Barstow, California too primitive Atta for a cash prize of one million dollars sixteen vehicles competed in the challenge and the all failed or crashed within the first ten miles of the journey. Now, finally went really fun feature of this book is that includes photographs of BF Skinner, Noam Chomsky, gray, Walter Rauch, Ashby, Warren, McCulloch Norman winer, Alan turing, Claude Shannon her. Simon Allen Newell, Oliver Selfridge John McCarthy. Frank, Rosa block, Peter Hart, Richard Duda. Judea Pearl David rebel heart James mccown, lend, Andy, Bartow, Richard Sutton, Marin Mincy and others when they were young adults the quest for artificial intelligence will be interest not only for AI newbies. But also engineer scientists and researchers will benefit from a high level overview of the evolutionary origins of current work from the first century to the twentieth century, the book sketches the major events which shaped the field of artificial intelligence machine learning as we know them today. In addition, the book does not assume a strong technical background. So it should be easily. Understood not only by scientists in the field. But also, the general public. So you can find out more on the website WWW dot learning machines went to win dot com. Thank you again for listening to this episode of learning machines went ah one. I like to remind you also that if you are member of the learning machines went went community lease update your user profile, and let me know what topics. She would like meet to cover in this podcast. You can update your user profile when you receive the Email newsletter by simply clicking on the let us know what you want to hear like if you're not a member of learning machines went went community. You can join the community by visiting our website at WWW dot learning. Machines went Owen dot com. And you will have the opportunity to update your user profile at that time, you can also post requests for specific topics or comments about the show in the statistical machine learning forum on Lincoln from time to time I will review the profiles of members of the learning machines went to went community and comments posted in the statistical machine learning Boreham on linked in and do my best to talk about topics of interest to the members of this group. And don't forget to follow us on Twitter. The Twitter handle for learning machines weta one is. Wena one talk. Also, please visit us on IT and Saliba review. We haven't had a review in a while. You can do this by going to the website WWW dot learning machines went to dot com and then clicking on the I team's icon. This will be very helpful to the podcast help us be more visible in. The search engines thank you so much your feedback in courage -ment are greatly valued. Thank you for participating in today's podcast with me. Dr Richard golden, you're encouraged to visit the website WWW dot learning machines went to one dot com. Where you have the opportunity to comment on today's podcast. Read the comments about their listeners obtain free supplemental references to related material associated with the show attain. A free copy of the notes for today's podcast free copies of notes from previous podcast episodes and free machine learning software and don't worry. This sound recording and its contents is copyright two thousand eighteen by army consulting Inc. All rights reserved us IC by Joe beat.

Dr Richard golden Peter Hart Twitter Walter Pitts George bull Lucy quences Professor Nelson Stanford University Professor LA Simon Allen Newell DARPA professor Neal Joe beat Stanford army consulting Inc United States