https://www.sciencedirect.com/science/article/pii/S1053811921001531 I just read the paper, some interesting points on testing cognitive maps with language and seeing if grid codes will fire. Their experiment consisted of creating audiovisual objects (words, shapes, and associated sounds) and had them mapped onto a 2D space. 31 participants were recruited and trained on 4 tasks and then finally tested… Continue reading Notes on “Grid-like and distance codes for representing word meaning in the human brain”
Tag: research
Notes on “No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit”
I just finished reading this paper. It is very relevant to the work I’m doing now on grid cells as I just reimplemented “Vector-based navigation using grid-like representations in artificial agents” in pytorch. I got similar results as in the paper, namely that only in specific circumstances could I get grid cells to appear in… Continue reading Notes on “No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit”
word2vec notes
I was amazed when word2vec first came out and it facinated me that such a powerful language model could be built so easily. I wanted to get a deeper understanding of the math behind it because I have some ideas on potential changes to it, so I thought I would try to implement the original… Continue reading word2vec notes
On Richard Feynman and your core questions
Richard Feynman famously wrote: “You have to keep a dozen of your favorite problems constantly present in your mind, although by and large they will lay in a dormant state. Every time you hear or read a new trick or result, test it against each of your twelve problems to see whether it helps. Every… Continue reading On Richard Feynman and your core questions
Notes on “A unified theory for the origin of grid cells through the lens of pattern formation”
I just read the paper, I’m still processing it, but here are some of my notes, thoughts and questions. https://papers.nips.cc/paper/2019/hash/6e7d5d259be7bf56ed79029c4e621f44-Abstract.html 3 Main models types in neuroscience: Descriptive explanations delineate an abstract characterization of aphenomenon, while mechanistic and normative explanations bridge abstractions of different levels.Mechanistic explanations show how a phenomenon emerges from lower-level components (e.g., howcircuit… Continue reading Notes on “A unified theory for the origin of grid cells through the lens of pattern formation”
Improve your learnings while reading by asking yourself pointed questions
I was just listening to a talk from Jim Kwik and he spoke about how retained more information while reading. He states its a complete waste of time if you are reading and not retaining information. He consciously asks 3 questions and takes notes as he is reading. How can I use this information? Why… Continue reading Improve your learnings while reading by asking yourself pointed questions
What do AI product and project managers (PMs) do?
Here are some questions you can ask them: What does your day to day look like? What level of technical skills is required? What do engineer managers do? what level of science is needed? What level of research is done by the PMs? Who do the PMs report to? What is the difference between the… Continue reading What do AI product and project managers (PMs) do?
Notes on “Design Principles of the Hippocampal Cognitive Map”
Paper link: https://papers.nips.cc/paper/2014/hash/dfd7468ac613286cdbb40872c8ef3b06-Abstract.html “We also propose that grid cells compute the eigendecomposition of place fields in part because is useful for segmenting an enclosure along natural boundaries. When applied recursively, this segmentation can be used to discover a hierarchical decomposition of space. Thus, grid cells might be involved in computing subgoals for hierarchical reinforcement learning.”… Continue reading Notes on “Design Principles of the Hippocampal Cognitive Map”
A review of “Grid-like Neural Representations Support Olfactory Navigation of a Two-Dimensional Odor Space”
I just finished reading “Grid-like Neural Representations Support Olfactory Navigation of a Two-Dimensional Odor Space” It’s an interesting paper that shows that olfactory(smell) seems to be represented with grid-like codes in the brain. The authors read and reference a bunch of papers where other researchers test if grid cells can represent other kinds of sensory… Continue reading A review of “Grid-like Neural Representations Support Olfactory Navigation of a Two-Dimensional Odor Space”
Evidence of Compositionality in the human brain
Artificial Intelligence and Cognitive Science researchers have taken for granted that compositionality exists in the human brain. Fodor , Chomsky, and many others have spoken about the human brain ability to create infinite meaning from a finite set of tokens (words). There are people who argue that the brain is not compositional. You can read… Continue reading Evidence of Compositionality in the human brain