Chapter
Biologically Realistic Hardware Neural Network
1:43:30 - 1:50:45 (07:14)
The use of biologically realistic hardware neural network helps to make large-scale neural networks much more feasible for extensive researches. The network has software and hardware implementation implications, whereas current GPU architectures are not useful, a graph chip would be useful.
Clips
Investigating the feasibility of making a large-scale biologically realistic neural network through the use of a hardware chip that emulates the Hodgkin-Huxley and Isakovich equations for biologically realistic neurons.
1:43:30 - 1:49:34 (06:03)
Summary
Investigating the feasibility of making a large-scale biologically realistic neural network through the use of a hardware chip that emulates the Hodgkin-Huxley and Isakovich equations for biologically realistic neurons. This method could be applied to simulate different parts of the brain and their interactions with each other to simulate human thought processes, which could be useful for geo-intelligence analysis applications.
ChapterBiologically Realistic Hardware Neural Network
Episode#103 – Ben Goertzel: Artificial General Intelligence
PodcastLex Fridman Podcast
The speaker discusses the limitations of current frameworks for graph processing and quantum machine learning, and proposes the possibility of making graph-centric quantum computers instead.
1:49:34 - 1:50:45 (01:10)
Summary
The speaker discusses the limitations of current frameworks for graph processing and quantum machine learning, and proposes the possibility of making graph-centric quantum computers instead. They also touch on the use of the Open-Cog software framework and cognitive architecture to determine algorithms for such machines.