YouSaid · the spoken record
Dileep George
- lines on the record
- 139
- first
- 2020-08-14
- most recent
- 2020-08-14
- sittings or episodes
- 1
- sources
- podcast
Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections
“And then within a layer of the neural network, the cortical neural network is much more structured within a level. There's a lot more intricate structure there. Even within an artificial neural network, you can think of in feature detection plus pooling as one level. And so that is kind of a microcircuit. It's much more complex in the real brain. So within a level, whatever is that circuitry within a column of the cortex and between the layers of the cortex, that's the microcircuit.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Correct. These are the cortical microcircuits. That's what neuroscientists use to talk about the circuits within a level of the cortex. So you can think of, you know, let's think in neural network, artificial neural network terms. People talk about the architecture of the, you know, how many layers they build, what is the fan in fan out, et cetera. That is the macro architecture.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Don't need to be, it doesn't need to be human interpretable. There is no need for it to be human interpretable. But it's almost like you will be able to find some interpretation of it because it is connected to the other things.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“The easiest way to think of it as a variable, right? It's a binary variable, which is showing the presence or absence of something.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Things like if I poke this higher level neuron, it will inhibit through this complicated loop through the thalamus, it will inhibit this other column. So they will do such experiments.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“And also, these cortical columns connect to a substructure called thalamus. So all cortical columns pass through this substructure. So our hypothesis is that the connections between the cortical columns implement this, you know, that's where the knowledge is stored about how these different concepts concepts connect to each other. And then the neurons inside this cortical column and in the thalamus in combination implement this actual computation in data for inference which includes explaining away and competing between the different hypotheses. And it is all very, so what is amazing is that neuroscientists have actually done experiments to the tune of showing these things. They might not be putting it in the overall inference framework, but they will show”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Encoding a concept, think of it as an example of a concept is an edge present or not or is an object present or not. So you can think of it as a binary variable, a binary random variable. The presence of an edge or not or the presence of an object or not. So each cortical column can be thought of as representing that one concept, one variable, and then the connections between these cortical columns are basically encoding the relationship between these random variables. And then there are connections within the cortical column. Each cortical column is implemented using multiple layers of neurons with very, very rich structure there. There are thousands of neurons in a cortical column.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“So, this is a paper that we are bringing out soon. Which one was this? This is the cortical microcircuits paper that I sent you a draft of. Of course, this is a lot of it is still hypothesis. One hypothesis that you can think of a cortical column”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Because now that piece of evidence is explained by the earthquaking being present. So if you think about these two causes explaining at lower level variable, which is alarm, now what we are saying is that increasing the evidence for some cause, there is evidence coming in from below for alarm being present. And initially it was flowing to a burglar being present. But now since there is side evidence for this other cause, it explains away this evidence and it evidence will now flow to the other cause. This is two competing causal things trying to explain the same evidence.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“So, this is the process of inference. One example of inference is having this exparing away effect between multiple causes. So graphical models can be used to represent causality in the world. So let's say you're... Or it can be triggered by an earthquake. Both can be causes of the alarm going off. So now you're in your office. You heard burglar alarm going off. You are heading home, thinking that there's a burglar. But while driving home, if you hear on the radio that there was an earthquake in the vicinity, now you're strength of evidence for a burglar getting into their house is diminished.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Then, so it cannot coding knowledge. And then once you encode the knowledge, you can do inference in the right way. What is the best way to explain some set of evidence using this model that you encoded? So when you encode the model, you are encoding the relationship between these different variables. How is the edge connected to the model of the object? How is the surface connected to the model of the object? And then, of course, this is a very distributed, complicated model. And inference is how do you explain a piece of evidence? A set of stimulus comes in. If somebody tells me there is a 50% probability that there is an edge here in this part of the model, how does that affect my belief on whether I should think that there should be a square represent in the image?”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, yeah. So neural networks are one class of machine learning models. You have a distributed set of nodes, which are called the neurons. Each one is doing a dot product, and you can approximate any function using this multi-level network of neurons. So that's a class of models which are used for function approximation. There is another class of models in machine learning called probabilistic graphical models. You can think of them as each node in that model is variable, which is talking about something. It can be a variable representing is an edge present in the input or not. At the top of the network, a node can be representing, is there an object present in the world or not?”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“And this inference includes projecting your model onto the evidence and taking the evidence back into the model and doing an iterative procedure. And this iterative procedure is what happens using the feed forward feedback propagation. And feedback affects what you see in the world. And it also affects feedforward propagation. Examples are everywhere. We see these kinds of things everywhere. The idea that there can be multiple competing hypotheses in our model trying to explain the same evidence. And then you have to kind of make them compete. And one hypothesis will explain a way the other hypothesis through this competition process.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes. Yeah. In fact, feedback connections are more prevalent in everywhere in the cortex. One way to think about it, and there's a lot of evidence for this, is inference. So basically, if you have a model of the world, and when some evidence comes in, what you are doing is inference. You are trying to now explain this evidence using your model of the world”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, I wouldn't put it as calculating the difference. It's more like what is the best explanation for the input stimulus based on the model of the world I have.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so this fits into a very beautiful picture about how the brain works. So the beautiful picture of how the brain works is that our brain is building a model of the world. So our visual system is building a model of how objects behave in the world. And we are constantly projecting that model back onto the world. So what we are seeing is not just a feed forward thing that just gets interpreted in a feed forward part. We are constantly projecting our expectations onto the world. And what the final percept is a combination of what we project onto the world combined with what the actual sensory input is.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Your visual system hallucinates the edges. And you can, when you look at it, you will see a faint edge, and you can go. Inside the brain and look, you know, do actually neurons signal the presence of this edge. And if they signal, how do they do it? Because they are not receiving anything from the input. The input is blank for those neurons. So how do they signal it? When does the signaling happen? So if a real contour is present in the input, then the neurons immediately signal, okay, there is an edge here. When it is an illusory edge, it is clearly not in the input. It is coming from the context. So those neurons fire later. And you can say that, okay, it's the feedback connections that is causing them to fire. And they happen later. And you can find the dynamics of them. So these studies are... Where do you perceive and very detailed”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“And the detail to which you can study this, it's amazing that you can actually not only find the temporal dynamics of when this happens. And then you can also find which layer in V1, which layer is encoding the edges, which layer is encoding the surfaces, and which layer is encoding the feedback, which layer is encoding the feed forward, and what's the combination of them that produces the final person. So, this is an example where it's a triangle, but the corners of the, only the corners of the triangle are shown in the stimulus. So they look like kind of Pac-Man”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“In this case, it turns out that it first settles on the edges. It converges on the edge hypothesis first, and then the surfaces are filled in from the edges to the inside.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Settle in the sense that you finally form the percept of the triangle. You understand where the contours of the triangle are, and you also know where the inside of the triangle is. That's when you form the final percept. Now you can ask what is the dynamics of forming that final percept. Do the neurons first find the edges and converge on where the edges are And then they find the inner surfaces, or does it go the other way around?”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“There is a very detailed micro circuit in V1 itself. There is organization within a level itself, the cortical sheet is organized into multiple layers and there are columnar structure. And this layer-wise and columnar structure is repeated in V1, V2, V4, IT, all of them. And the connections between these layers within a level. In V1 itself, there are six layers, roughly. And the connections between them, there is a particular structure to them. Now, so one example of an experiment people did is when you present a stimulus, which is, let's say, requires separating the foreground from the background of an object. So it's a textured triangle on a textured background. You can tick, does the surface settle first or does the contour settle first?”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, yeah, there's another pathway. Okay, so I'm talking about just the object recognition pathway. All right, cool. And then in V1 itself, so it's.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Very, very fascinating experiments. So I can give you one example I was impressed with. So before going to that, let me give you an overview of how the layers in the cortex are organized. Visual cortex is organized into roughly four hierarchical levels. V1, V2, V4, IT.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“I mean, it's not a random exploration at all. It's a very hypothesis driven, right? They are very, experimental neuroscientists are very, very systematic in how they probe the brain because experiments are very costly to conduct. They take a lot of preparation. They need a lot of control. So they are very hypothesis driven in how they probe the brain. And often what I find is that when we have a question in AI about has anybody probed how lateral connections in the brain works? And when you go and read the literature, yes, people have probed it and people have probed it very systematically. And they have hypothesis about how those lateral connections are supposedly contributing to visual processing. But of course, they haven't built very, very functional detailed models of it.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, quite a lot of things. So, one is if you look at the visual cortex and visual cortex is a large part of the brain. I forgot the exact fraction, but it's a huge part of our brain area is occupied by just vision. So vision cortex is not just a feed forward cascade of neurons. There are a lot more feedback connections in the brain compared to the feed for word connections. And it is surprising to the level of detail neuroscientists have actually studied this. If you go into neuroscience literature and poke around and ask, have they studied what will be the effect of poking a neuron in level IT in level V1 and have they studied that? And you will say, yes. Have studied that so every”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Those are beautiful. And at the same time, those do not itself by themselves convey the story of how does it work. And somebody has to understand okay, why are they connected like that? And what are those things doing? And we do that by building models in AI using hints from neuroscience and repeat the cycle.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“More about does the model actually work? And you can refine the model, find better ways of putting these neuroscience insights together So I would say neuroscientists alone just from experimentation will not be able to build a model of the brain, a functional model of the brain. There's lots of efforts which are very impressive efforts in collecting more and more connectivity data from the brain. How are the micro circuits of the brain connected with each other?”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“And then building that model which functions, which is a functional model, which is doing the task that we want the model to do, it is not just trying to model a phenomena in the brain. It is trying to do what the brain is trying to do on the whole functional level. And building that model will help you fill in the missing pieces that biology just gives you the hints. building the model fills in the rest of the pieces of the puzzle and then you can go and connect that back to biology and say okay now it makes sense that this part of the brain is doing this or this layer in the cortical circuit is doing this and then continue this iteratively because now that will inform new experiments in neuroscience and of course you know building them and verifying that in the real world will you will also tell you”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Exactly. But again, I can tell from the point of objectively what are the things that we know about the brain and how that can be used to build AI models, which can then go back and inform how the brain works. So my way of understanding the brain would be to basically say, look at the insights neuroscientists have found, understand that from a computational angle, information processing angle.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“So timelines are very, very hard to predict. And you can, of course, be wrong. And it can be wrong on either side. We know that when we look back the first flight was in 1903. In 1900, there was a New York Times article on flying machines that do not fly. And humans might not fly for another hundred years. That was what that article stated. But no, they flew three years after that. So it's very hard to, so...”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“By observing the brain. They do find good insights. But those insight cannot be put together just as a simulation. You have to investigate what are the computational underpinnings of those findings. How do all of them fit together from an information processing perspective? You have to, somebody has to painstakingly put those things together and build hypothesis. So I don't want to this all of neuroscience is saying, oh, they are not finding anything. No, that paper almost went to that level of neuroscientists will never understand. That's not true. I think they do find lots of useful things, but it has to be put together in a computational framework.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“So I'm very familiar with this particular paper. I think it was called Can a Neuroscientist Understand a microprocessor or something like that. Following the methodology in that paper, even electrical engineer would not understand microprocessors. So I don't think it is that bad in the sense of saying neuroscientists do find valuable things.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Understand how a microprocessor works, but you say, Oh, I now can model one transistor well, and now I will just try to interconnect the transistors according to whatever I could guess from the experiments and try to simulate it, then it is very unlikely that you will produce a functioning microprocessor. When you want to produce a functioning microprocessor, you want to understand Boolean logic, how do the gates work, all those things. And then understand how do those gates get implemented using transistors.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“And these models, because they are going to the level of mechanism, right? So they are basically looking at, okay, what is the effect of turning on an ion channel? And you can model that using electric circuits. So it is not just a function fitting. People are looking at the mechanism underlying it and putting that in terms of electric circuit theory, signal propagation theory, and modeling that. Those models are sophisticated, but getting a single neurons model, 99% right, does not still tell you how to, you know, it would be the analog of getting a transistor model right and now trying to build a microprocessor. And if you just observe, if you did not understand,”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Oh, well, actually, they are pretty detailed and pretty sophisticated. And they do replicate the neural dynamics. If you take a single neuron and you try to turn on the different channels, the calcium channels and the different receptors and see what the effect of turning on off those channels are in the neurons spike output. People have built pretty sophisticated models of that and they are, I would say, you know, in the regime of correct.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so the Blue Brain Project, the original idea as proposed was you put very detailed biophysical neurons of neurons and you interconnect them according to the statistics of connections that we have found from real neuroscience experiments and then turn it on and see what happens. And these neural models are incredibly complicated in themselves because these neurons are modeled using this idea called Hodgkin-Huxley models, which are about how signals propagate in a cable. And there are active dendrites, all those phenomena, which those phenomena themselves we don't understand that well. And then we put in connectivity, which is part guesswork, part. Take whatever comes out of it as okay, this is something interesting”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Understand the nature of evil. Or as it happens in most of the simulations, you easily get one thing out, which is oscillations. If you simulate a large number of neurons, they oscillate. And you can adjust the parameters and say that, oh, oscillations match the rhythm that we see in the brain, etc.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Human brains and rat brains or cat brains have lots in common that the neocortex structure is very similar. So initially they were trying to just simulate a cat brain.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes, if you want to build the brain, we definitely need to understand how it works. So Blue Brain or Henry Markham's project is trying to build a brain without understanding it. Just trying to put details of the brain from neuroscience experiments into a giant simulation by putting more and more neurons, more and more details. But that is not going to work because When it doesn't perform as what you expect it to do, then what do you do? You just keep adding more details. How do you debug it? So unless you understand, unless you have a theory about how the system is supposed to work, how the pieces are supposed to fit together, what they're going to contribute, you can't build it.”
2020-08-14 · Lex Fridman Podcast · #115 – Dileep George: Brain-Inspired AI · IDENTIFIED FROM THE TRANSCRIPT · source