If you are into hippocampus, PFC, cognitive maps etc. you’d have encountered Successor Representations (SR). But often SR is misunderstood, and ascribed properties it doesn’t have. In this blog I describe some of the limitations of SR as a model of cognitive maps.
https://blog.dileeplearning.com/p/a-critique-of-successor-representations
Have a look at our recent paper, and the associated blog to change how you think about hippocampus. https://www.science.org/doi/10.1126/sciadv.adm8470
"Space is a latent sequence: A theory of the hippocampus"
The blog explains, with animated visuals, how interpreting sequential responses of hippocampal neurons in spatial/Euclidean terms is problematic.
https://blog.dileeplearning.com/p/space-is-a-sensory-motor-sequence
Planning to participate in the ARC price to win a million bucks? Read this blog first!
https://blog.dileeplearning.com/p/how-to-get-a-million-bucks-quick
The abstract reasoning corpus (ARC) challenge by Francois Chollet has gained renewed attention due to the 1M prize announcement. This challenge is interesting to me because the idea of “abstraction” as “synthesizing cognitive programs” is something my team has worked on and
We present a variational Monte Carlo algorithm for estimating the lowest excited states of a quantum system which is a natural generalization of the estimation of ground states. The method has no free parameters and requires no explicit orthogonalization of the different states, instead transforming the problem of finding excited states of a given system into that of finding the ground state of an expanded system. Expected values of arbitrary observables can be calculated, including off-diagonal expectations between different states such as the transition dipole moment. Although the method is entirely general, it works particularly well in conjunction with recent work on using neural networks as variational Ansatze for many-electron systems, and we show that by combining this method with the FermiNet and Psiformer Ansatze we can accurately recover vertical excitation energies and oscillator strengths on molecules as large as benzene. Beyond the examples on molecules presented here, we expect this technique will be of great interest for applications of variational quantum Monte Carlo to atomic, nuclear and condensed matter physics.
Cool post by Dileep George (@dileeplearning) pointing out that there likely are fundamental limits on what we can achieve by scaling up LLMs, and introducing a useful metaphor: scaled up zeppelins vs. underperforming airplanes in the early 20th century.
https://dileeplearning.substack.com/p/welcome-to-the-exciting-dirigibles-500
David Pfau
Jelle Zuidema