YouSaid · the spoken record

Ben Goertzel

lines on the record: 334
first: 2020-06-22
most recent: 2020-06-22
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

“These are recognizing a large number of shallow patterns. They're not forming an abstract representation. And that's the point I was coming to when we're looking at grammar induction. We tried to mine patterns out of the structure, the transformer network You can, but the patterns aren't what you want, they're nasty. So, I mean, if you do supervised learning, if you look at sentences where you know the correct parts of a sentence, you can learn a matrix that maps between the internal representation of the transformer and the parse of the sentence, and And so then you can actually train something that will output the sentence parse. From the Transformer Network's internal state, and we did this, I think. Christopher Manning, some others have not done this also.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Any more than a faster car is going to get you the Mars, yeah. A completely different kind of thing. I mean, these networks are very cool. And as an entrepreneur, I can see many highly valuable uses for them. And as an artist, I love them, right? So, I mean, we're using our own neural model, which is along those lines to control the Philip K. Dick robot now. And it's amazing to train a neural model on the robot Philip K. Dick and see it come up with crazed stoned philosopher pronouncements, very much like what Philip Kdick might have said, right? So these models are super cool. And I'm working with Hansen Robotics now on using a similar but more sophisticated one for Sophia, which we haven't launched yet. So I think it's cool. But it's not on.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Lucas Kaiser and a bunch of these guys create transformer networks, that classic paper like attention is all you need and all these things following on from that. So we're looking at transformer networks and like These are able to, I mean, this is what underlies GPT 2 and GPT 3 and so on, which are very, very cool and have absolutely no cognitive understanding of any of the texts they're looking at. They're very intelligent idiots, right?”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But just as an intellectual exercise, as a learning exercise, trying to learn grammar from a corpus is very, very interesting, right? And that's been a field in AI for a long time. No one can do it very well. So we've been looking at transformal neural networks and tree transformers, which are amazing. These came out of Google Brain, actually. On that team was Lucas Kaiser, who used to work for me and won the period 2005 through eight or something. So it's been fun to see my former sort of AGI employees disperse and do all these amazing things with way too many sucked into Google, actually.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, yeah, yeah. On the other hand, so I'm more interested in that, I'm more interested in making an AGI system learn language from its social and embodied experience. On the other hand, That's also more of a pain to do, and that would lead us into Hansen robotics and their robotics work, I've known which we'll talk about in a few minutes.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I mean, the way a human learns language is not that, right? I mean, we learn from language that's used in context. So it's a social embodied thing. We see how a given sense is grounded in observation.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So, this isn't AGI either, but it's sort of on the verge between Norway and AGI or something. On supervised grammar induction is the problem. Throw your AI system, a huge body of text, and have it learn the grammar of the language that produced that text. So you're not giving it labeled examples, so you're not giving it like a thousand sentences where the parsers were marked up by graduate students. So it's just got to infer the grammar from the text. It's like the rosetta stone, but worse, right? Because you only have the one language. And you have to figure out what is the grammar. So that's not really AGI because”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I'm there bad, but there's many ways that you could deal with that. So I've been wrestling with this a lot in some work on supervised grammar induction, and I have a simple paper on that that I'll give it the next AGI conference, the online portion of which is next week, actually.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“That just hadn't been one of our design thoughts when we built Open COG, right? So between wanting really fast dependent type checking and wanting much more efficient interoperation between the computation graphs of deep neural net frameworks and OpenCOG hypergraph and adding on top of that wanting to more effectively run an OpenCog hypergraph AGI paradigm doesn't really change. The mathematics is the same. It's just we can't scale to the level that we want in terms of distributed processing or speed of various kinds of processing with the current infrastructure that was built in the phase 2001 to 2008, which is hardly shocking.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So we took what came out of all the deep neur models for the different cameras, we fed it into an open cog symbolic representation. Then we did some pattern mining and some reasoning on what came out of all the different cameras within the symbolic graph. And that worked well for that application. I mean, Hugo Latapi from Cisco gave a talk touching on that at last year's AGI conference. It was in Shenzhen. On the other hand, we learned from there it was kind of clunky to get the deep neural models to work well with the symbolic system because We were using torch and torch keeps a sort of computation graph but you needed like real-time access to that computation graph within our hypergraph and we certainly did it. Alexei Polapov, who leads our St. Petersburg team, wrote a great paper on cognitive modules in OpenCog explaining sort of how do you deal with the torch compute graph inside OpenCog. But in the end, we realized like...”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“For Cisco, for example, which was on this was street scene analysis, but they had deep neuromodels for a bunch of cameras watching street scenes. But they trained a different model for each camera because they couldn't get the transfer learning to work between camera A and camera B.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So, yeah, with the true AGI system, we're sticking with this same basic architecture, but we're trying to build on what we've learned. One thing we've learned is that we need type checking among dependent types to be much faster and among probabilistic dependent types to be much faster. As it is now, you can have complex types on the nodes and links. But if you want to put types to be first class citizens so that you can have the types can be variables and then you do type checking among complex higher order types, you can do that in the system now, but it's very slow. This is stuff like is done in cutting edge program languages like Agda or something, these obscure research languages. On the other hand, we've been doing a lot tying together deep neural nets with symbolic learning. So we did a project.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Starting point for your HTML. Yeah, but I like True better because True has like, you can be true-hearted, right? You can be true to your girlfriend. True has a number and it also has logic in it, right? Because logic is a key.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, we're also calling it true AGI, so we're not quite sure what the name is yet. We made a website for true AGI.io, but we haven't put anything on there yet. We may come up with an even better name.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“On the back end, but we haven't, that's not the AGI goal, right? It's interesting, but it's not the AGI goal. So now what we're looking at with our rebuild at the system.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“In the hierarchical neural network. But I would say we have taken that direction of taking the types of knowledge you need for different types of learning like declarative, procedural attentional, and how do you make these types of knowledge represent in a way that allows cross-learning across these different types of memory? We've been prototyping and experimenting with this OpenCog, and before that web mine since the mid nineteen nineties. Now, disappointingly to all of us, this has not yet been cashed out in an AGI system, right? I mean, we've used this system within our consulting business, so we've built natural language processing and robot control and financial analysis. We've built a bunch of sort of vertical market-specific proprietary AI projects that use OpenCog on”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“It was quite a horrible mess. So, as well as shifting and implementation where the graph is its own object and the agents are separately scheduled, we've also done a lot of work on how do you represent programs, how do you represent procedures, how do you represent genotypes for evolution in a way that the interoperability between the different types of learning associated with these different types of knowledge actually works. And that's been quite difficult. It's taken decades and it's totally off to the side of what the commercial mainstream of the AI field is doing, which isn't thinking about representation at all, really. Although you could see like in the DNC, they had to think a little bit about how do you make representation of a map in this memory matrix work together with a representation needed for, say, visual pattern recognition.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“There's a long list of technical answers there, which will take a while to go through, right? And this has been decades of work. I mean, the first AI system of this nature I tried to build was called WebMind in the mid-1990s. And we had a big graph, a big graph operating in RAM implemented with Java 1.1, which is a terrible, terrible implementation idea. And then each node had its own processing. So the core loop looped through all nodes in the network and let each node enact what its little thing was doing. And we had logic and neural nets in there, but an evolutionary learning, but we hadn't done enough of the math to get them to operate together very cleanly. So it was really.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, yeah, given the resource constraints at hand, you can map it back and forth to your term logic fast enough and without having a bloated logic expression, right? So there's just a lot of... There's a lot of nitty gritty particulars there, but by the same token, if you ask a chip designer, like how do you make the Intel i7 chip so good?”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Can you boil down your procedure into a bunch of nodes and links in a way that's like hierarchically decomposed and simple enough?”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So every program can be mapped into a proof. Every proof can be mapped into a program. You can model this using category theory and a bunch of nice math. But we want to make that practical, right? So that if you have an executable program that moves a robot's arm or figures out in what order to say things in a dialogue, that's a procedure represented in OpenCog's hypergraph. But if you want to reason on how to improve that procedure, you need to map that procedure into logic using Curry Howard, the isomorphism, so that then the logic engine can reason about how to improve that procedure and then map that back into the procedural representation that is efficient for execution. So again, that comes down to not just can you make your procedure into a bunch of nodes and links, because I mean, that can be done trivially. A C++ compiler has nodes and links inside it.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Form than is to simplify logic expression to a comprehensible form, but it doesn't come for free. What's in the AI's mind is incomprehensible. Voodoo there. I mean, if you're familiar in computer science or something called the Curry Howard correspondence, which is a one-to-one mapping between proofs and programs.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“It's tough. In simple cases, it's interpreted by humans. But honestly. I would say logic systems give more potential for. Transparency and comprehensibility than neural net systems, but you still have to work at it. Because, I mean, if I show you a predicate logic proposition with like 500 nested universal and existential quantifiers and 217 variables, that's no more comprehensible than the weight matrix of a neural network, right? So I'd say the logic expressions in AI learns from its experience are mostly totally opaque to human beings. And maybe even harder to understand than because, I mean, when you have multiple nested quantifier bindings, it's a very high level of abstraction. There is a difference, though, in that within logic, it's a little more straightforward to pose the problem of like normalize this and boil this down to a certain form. I mean, you can do that in neural nets too. Like you can distill a neural net to a simpler form, but that's more often done to make a neural net that'll run on an embedded device or something. It's harder to distill a net to a comprehensive.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Logic relations, including basic sort of propositional logic relations, as Aristotleian term logic deals with, and then quantifier logic relations also, how do you break those down elegantly into a hypergraph? Because you can boil logic expression into a graph in many different ways. Many of them are very ugly, right? We tried to find elegant ways of sort of hierarchically breaking down complex logic expression into nodes and links so that If you have, say, different nodes representing Ben, AI, Lex, interview, or whatever, the logic relations between those things are compact in the node and link representation so that when you have a neural net acting on those same nodes and links, the neural net and the logic engine can sort of interoperate with each other.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Focus of attention should make me the focus of attention, right? So you could have then a neural link and you could have a symbolic logical inheritance link in your term logic and they have separate meaning, but they could be used to guide each other as well. If there's a large amount of neural weight on the link between A and B that may direct your logic engine to think about, well, what is the relation? Are they similar? Is there an inheritance relation? Are they similar in some context? On the other hand, if there's a logical relation between A and B, that may direct your neural component to think, well, when I'm thinking about A, I'd be directing some attention to be also because there's a logical relation. So in terms of logic, there's a lot of thought that went into how do you break down”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“This link is B implies C, then deduction builds a link A implies C and your probabilistic algorithm can assign a certain weight there. Now you may also have like a heavy and neural link from A to C, which is the degree to which A being”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So term logic was invented by Aristotle, or at least that's the oldest recollection we have of it. But term logic breaks down basic logic into basically simple links between nodes, like an inheritance link between node A and node B. So in term logic, the basic deduction operation is A implies B, B implies C, therefore A implies C. Whereas in predicate logic, the basic operation is modus ponens, like A, A implies B, therefore B. So there's a slightly different way of breaking down logic, but by breaking down logic into term logic, you get a nice way of breaking logic down into nodes and links. So your concepts can become nodes, the logical relations become links. And so then inference is like, so if this link is A implies B,”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Kind of type system. Yeah, yeah. So, this gets very nitty gritty and mathematical, of course. One key part is switching from predicate logic to term logic.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Intermediate state with the neural net and with the evolutionary learning algorithm so that they can help each other out of bottlenecks and help each other solve combinatorial explosions by intervening inside each other's cognitive processes. But that can only be done if the intermediate state of a logic engine and the evolutionary learning engine and a deep neural net are represented in the same form. And that's what we figured out how to do by putting the right type system on top of this weighted labeled hypergraph.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“What fascinates me is finding a common representation that underlies the Abstract declarative knowledge and sensory knowledge and movement knowledge and procedural knowledge and episodic knowledge, finding the right level of representation where all these types of knowledge are stored in a sort of universal and interconvertible yet practically manipulable way, right? So to me, that's the core, because once you've done that, then the different learning algorithms can help each other out. Like what you want is if you have a logic engine that helps with declarative knowledge and you have a deep neural net that gathers perceptual knowledge and you have, say, an evolutionary learning system that learns procedures, you want these to not only interact on the level of sharing results and passing inputs and outputs to each other, you want the logic engine when it gets stuck to be able to share its interest.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Can contain programs In the current version, it is a very inefficient way to guide the execution of programs, which is one thing that we are aiming to resolve with our rewrite of the system now.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Many different types of semantics, which means you could make a horrible, ugly mess, or you could make a system where these different types of knowledge all interpenetrate and synergize with each other beautifully, right?”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“And then it's choosing what collection of agents, what collection of AI algorithms or processes are going to run to operate on this hypergraph. And of course, those two decisions are closely connected to each other. So in terms of the type system, there are some links that are more neural net-like. They just like have weights to get updated by Hebbian learning and activation spreads along them. There are other links that are more logic-like and nodes that are more logic-like. So you could have a variable node, and you can have a node representing a universal or existential quantifier, as in predicate logic or term logic. So you can have logic-like nodes and links, or you can”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so within this framework, then, creating a cognitive architecture is basically two things. It's choosing what type system you want to put on the nodes and links in the hypergraph, what types of nodes and links you want.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“That's the growing graph. Yeah, that's true. It is different model than, say, current deep neural nets and have a fixed neural architecture and you're updating the weights. Although there have been like cascade correlational neural net architectures that grow new nodes and links. But the most common neural architectures now have a fixed neural architecture. You're updating the weights. And in open cog, you can update the weights, and that certainly happens a lot. But adding new nodes, adding new links, removing nodes and links is an equally critical part of the system's operations. Got it.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“That's the software framework, right? So then the next thing is our cognitive architecture tells us particular algorithms to put there.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You're still putting a square peg into a round hole in a certain way. The same is true. I mean, quantum machine learning, which is very cool. It's also all about how to get matrix and vector operations in quantum mechanics. And I see why that's natural to do. I mean, quantum mechanics is all unitary matrices and vectors, right? On the other hand, you could also try to make graph-centric quantum computers, which I think is where things will go. And then we can take the OpenCog implementation layer implement it in an uncollapsed state inside a quantum computer. But that may be the singularity squared, right? I'm not sure we need that to get to human level.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Having neuromorphic hardware that really let you simulate like a realistic model of the neuron would be amazing. But that's sort of with my computational neuroscience hat on, right? With an AGI hat on, I'm just more interested in these hypergraph knowledge representation-based architectures, which would benefit more from various types of graph processors because the main processing bottleneck is reading, writing to RAM. It's reading, writing to the graph in RAM. The main processing bottleneck for this kind of proto-AGI architecture is not multiplying matrices. And for that reason, GPUs, which are really good at multiplying matrices, don't apply as well. There are frameworks like Gunrock and others that try to boil down graph processing to matrix operations, and they're cool.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Biologically realistic neural networks. Now, what's been done so far is not like that. So I guess personally as a researcher, I mean, I've done a bunch of work in cognitive neuroscience, where I did some work with IRPA in DC intelligence adventure research project agency. We were looking at how do you make it biologically realistic simulation of seven different parts of the brain cooperating with each other using realistic nonlunar dynamical models of neurons and how do you get that to simulate what's going on in the mind of a geoint intelligence analyst while they're trying to find terrorists on a map, right? So if you want to do something like that.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Have not been great. Look, for example, if you wanted to make a biologically realistic hardware neural network, like Circuit in hardware that emulated like the Hodgkin Huxley equation or the Ishakevich equation, like differential equations for a biologically realistic neuron, and putting that in hardware on the chip, that would seem that it would make more feasible to make a large scale truly”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“That I'm working on. I think if, you know. In principle, no morphic computing should be amazing. I haven't yet been fully sold on any of the systems that are out there, like Memristors should be amazing too, right? So a lot of these things Obvious potential, but I haven't yet put my hands on the system that seemed to manifest that. Yeah, Markism should be.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I'm excited about graph processors because I think they can massively speed up OpenCog, which is a class of architectures that I'm”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“A graph chip would be incredibly useful, right? And I think GraphCore has those now, but they're not ideally suited for this. But I think in the next, let's say three to five years, we're going to see new chips where like a graph is put on the chip and the back and forth between multiple processes acting SIMD and MIMD on that graph is going to be fast. And then that may do for OpenCog type architectures, what GPUs did for deep neural architecture.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So, in theory, they could do anything they want to do, they're just C processes. On the other hand, the computation framework is sort of designed for agents where most of their processing time is taken up with reads and writes to the atom space. And so that's a very different processing model than, say, the matrix multiplication-based model. Shared memory among different cognitive processes, but it also has software and hardware implementations because current GPU architectures are not so useful for OpenCOG, whereas”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, I'm sure they did. And a guy named Ben Draibus, who's a mathematician, a professor in Louisiana, or somewhere Had a beautiful book on quantum sets and hypergraphs and algebraic topology for discrete models of physics and carried it much farther than Wolfram has, but he's not rich and famous. So it didn't get in the headlines. But yeah, Wolfram aside, yes, certainly that's a good way to put it. The whole OpenCog framework. Could use it to model biological networks and simulate biology processes. You could use it to model physics on discrete graph models of physics. You could use it to do Say biologically realistic neural networks, for example. And so that's a framework.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, that's right. And I would add on that note the idea of using hypergraph type models in physics is not very new. If you look at”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“A scheduler, and each of these agents basically reads stuff from the Abbaspace and it writes stuff to the Abbas space. So this is sort of the basic operational model.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Then one way to do that is make that link go to that whole subgraph representing the body of information. There are many alternate representations, but that's anyway what we have in OpenCOG, we have an atom space, which is this weighted label generalized hypergraph, knowledge store, it lives in RAM, there's also a way to back it up to disk. There are ways to spread it among multiple different machines. Then there are various utilities for dealing with that. So there's a pattern matcher which lets you specify a sort of abstract pattern and then search through a whole atom space labeled hypergraph to see what sub hypergraphs may match that pattern for an example. So that's then there's something called the cog server in OpenCog, which lets you run a bunch of different agents or processes”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“To work well here. Got it. Right, right, right. And so similarly, you could have a link to a whole graph because a whole graph could represent, say, a body of information. And I could say, I reject this body of information.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Can you reduce hypergraph to a graph and you could reduce a graph to an adjacency matrix? There's always multiple representations.”
2020-06-22 · Lex Fridman Podcast · #103 – Ben Goertzel: Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source