
29 segments available
This is a talk for course 6.S099: Artificial General Intelligence. This class is free and open to everyone. Our goal is to take an engineering approach to exploring possible paths toward building human-level intelligence for a better world. INFO: Course website: https://agi.mit.edu AI podcast: https://lexfridman.com/ai CONNECT: - If you enjoyed this video, please subscribe to this channel. - AI Podcast: https://lexfridman.com/ai/ - Show your support: https://www.patreon.com/lexfridman - LinkedIn: https://www.linkedin.com/in/lexfridman - Twitter: https://twitter.com/lexfridman - Facebook: https://www.facebook.com/lexfridman - Instagram: https://www.instagram.com/lexfridman - Slack: https://deep-mit-slack.herokuapp.com
Nadir Bin Ski introduces cognitive architecture as a key approach to achieving artificial general intelligence (AGI), detailing its interdisciplinary roots and contextualizing the discussion with personal inspirations.
"so today we have nadir bin ski he's a professor at Northeastern University working on various aspects of computational agents that exhibit human level intelligence please give Nate a warm welcome than..."
Exploring the need for AI systems that can learn over time and adapt to tasks they haven't encountered.
"and other sorts of maybe AI machine learning systems we want systems that are going to persist for a long period of time we want them robust to different conditions we want them learning over time and..."
This segment explores how modeling human cognition can advance AI systems and applications.
"knowledge work on hard problems great I think there are folks who are in kind of that middle cognitive modeling realm and so I'll use this term a lot it's really understanding how humans think how hum..."
This segment discusses the challenges and principles of predicting human behavior and task performance in cognitive modeling.
"act that way but by some definition of thinking we want the system to do what humans do or at least be able to make predictions about it so that might be things like what errors would the human make o..."
Exploring how practice affects reaction times in task performance.
"the target so both moving along distance will take a while but also if you're aiming for a very small point that can take longer then if there's a large area that you just kind of have to get yourself..."
This segment discusses Alan Newell's concept of cognitive architecture, which aims to unify various cognitive theories to understand human intelligence in tasks like chess.
"they make they played a few games how would they adapt themselves or if we want to develop system that ended up being good at chess or at least learning to become better at chess my question is if you..."
This segment explores the concept of lactose ium in the context of software representing scientific theories and tracking progress.
"question asked is okay so we've gone from a methodology of science that we understand how to operate in we make a hypothesis we construct a study we gather our data we evaluate that data and we falsif..."
This segment explores the concept of bounded rationality in cognitive architecture and how it shapes our understanding of human decision-making and task execution.
"building up to deliberate tasks that occur in the brain and tasks that are operating on the order of ten seconds some of these might occur in the psychology laboratory but probably a step up to and ou..."
This segment explores the concept of satisficing in decision-making under cognitive constraints and complexity.
"amount of memory short-term as well as long-term as well as other aspects of our computing infrastructure that are going to keep us from being able to arbitrarily solve complex problems as well as how..."
This segment discusses the evolution of cognitive architectures from logical representations to incorporating non-symbolic and perceptual processing in AI.
"the neuronal infrastructure that we have but if we got the software right we could implement it in the bits bytes Ram and processor that make up modern computers that's kind of the weakest way to look..."
This segment discusses psychological modeling in AI, focusing on systems like Soar and Sigma that aim to replicate human cognitive processes.
"biological processes at a layer above there would be psychological modeling which is to say trying to build systems that are true in some sense to areas of the brain interactions in the brain and bein..."
This segment discusses the potential of building cognitive architectures for AI using innovative models and tools.
"the on environment and actually forgive separately and silently on medical side we all know that we have cognitive town concession we get over and we can try that address accountant spicy alienating p..."
This segment explores how AI agents perceive, learn, and select actions in both digital and real-world environments.
"state of the system and perform internal computations but also about external actuation and external might be a digital system a game AI but it might also be some sort of robotic actuation in real wor..."
This segment explores how the ACT-R cognitive architecture enables reactive learning and complex behavior through procedural models and predictions about human cognition.
"let's take Wikipedia and let's just stick it in the brain of the system there'll be more tasks in general but then also whatever it is that you're doing right now how should you proceed in that and th..."
This segment discusses Akhtar Sigma's advanced capabilities and its role in modern machine learning and robotics.
"interested in it the main distribution is in Lisp but many people have used this and wanted to apply it to systems that need a little more processing power so there's the NRL has a Java port of it tha..."
This segment discusses the critical importance of maintaining a response time under 50 milliseconds in robotics and AI applications to avoid delays and enhance user experience.
"number that comes out which is 50 milliseconds which is to say in terms of responding to tasks if you're above that time humans will sense a delay and you don't want that to happen now if we're workin..."
This segment explores an interactive dance experience where virtual dancers learn from human movements through improvisation and cognitive theories.
"collective dance experiences allowing the depends to create an explorer movement while having fun the development of lumini has been a hundred exploration in our forms of theatre and dance as well as ..."
This segment explores how agents understand and learn tasks through sensory input and experience, detailing the processes involved in achieving goals and refining their capabilities.
"so you can look a little bit at top left in terms of the pointers you're going to see some text commands being entered so what kind of attribute is blue we're gonna say it's a color and so that can ma..."
This segment explores how leveraging human memory principles can enhance AI's word sense disambiguation tasks.
"before we get input in this perception called the input link rules are going to fire all in parallel and say here's everything I know about the situation here's all the things I could do decision proc..."
This segment explores how implementing a forgetting mechanism in cognitive architectures can enhance efficiency in memory usage and decision-making.
"multiple corpora so we said okay this seems like a reasonable mechanism let's look at implementing this efficiently in the architecture and the problem was this term right here said for every memory f..."
This segment explores how memory decay improves the performance and efficiency of a mobile robot and reinforcement learning in a dice game scenario.
"being a fairly close approximation one that as compared to an accurate completely accurate search for the value ended up being somewhere between 15 to 20 times faster and so when we looked at our mobi..."
This segment discusses the ongoing challenges and considerations in developing human-level AI, emphasizing integration and the relevance of various cognitive architectures.
"so just to bring back why I went through this story was we had a problem we looked to our example of human level AI which is humans themselves we took an idea it turned out to be beneficial we found i..."
This segment dives into the use of heuristics in cognitive architectures, highlighting the efficiency of processing changes and specific task adaptations.
"build a brain really cool read download the software go through toriel's it's it's really great how can the human mind occur in the physical universe is one of the court akhtar books so it talks throu..."
This segment discusses the potential for integrating heuristic search methods with deep learning systems, highlighting the challenges and solutions in merging different cognitive architectures.
"you do that's so true and I'm the first thing that comes to my mind are local search methods okay so one thing is you can actually implement heuristic search in rules in the system and that's actually..."
Exploring how AI systems manage forgetting and reconstructing memory to maintain efficiency and task performance.
"pre-processing the the the sensory input or post-processing their draft but the other one that would be another way of combining two system and that's actually what's going on in the rosey system so t..."
This segment explores the importance of forgetting in AGI systems and its implications for cognitive modeling and human interaction.
"has there been any exploration of learning the forgetting process just doing something complicated or interesting with which parts to forget or not the closest I will say was kind of a metacognition p..."
This segment discusses the advantages and limitations of cognitive architecture in achieving human-level artificial intelligence.
"procedure by which if I have a set of preferences to make a very quick and clean decision so what's basically happened is you've pushed the hard questions of how to make complex decisions about action..."
Exploring the challenges and aspirations of achieving human-level AI, emphasizing the importance of persistence, creativity, and adaptation in research.
"hard it's challenging it's ambitious to say that's the goal because for decades we haven't done it it's extraordinarily hard it it is less difficult in some ways to constrain it yourself down to a sin..."
This segment discusses how analyzing text properties can enhance our understanding of human cognition and improve cognitive modeling.
"they were based their original inspirations were based off of human cognition and and because humans can't remember everything so were there any instances of the other way around where some discovery ..."