Research topic recommendation for bachelor thesis

[Bitking]

@BullShark

Bitking, if I understand correctly, the hex-grid coding works on top of vanilla HTM? What is the current state of the technical details of this idea? For implementing this idea a theoretical framework is needed that has progressed enough to be almost ready to be literaly translated into code. Can you estimate how much research is needed before we get to this point where you can actually write code for this?

Pieter,
My work is almost entirely based on simulations of the cells in the cortex and is completely unlike anything anyone else the people in this forum are doing. The test set, environment, and tool set are all in straight C and Perl. HTM happens to be one of the test configurations. Inputs are 2D maps of activation bits and maps of connections strengths, processing is all done on interactions of layers of maps, and the output is a map of bits.

How I do dendrites and synapses is somehow different than what anyone else here is doing.

Path based SDRs (Dendrite Trees)

In an earlier post, I mentioned that I have been trying to work out how to form the cortical.io retina using HTMs. This effort has led me to work through what operations are being performed by HTMs and how to compute with these primitives. The basic task of the conversion between a stream of data and a spatial distribution of the semantically related SDRs requires that the somewhere in the computations there is a sense of location in the cell bodies. I also wanted to work within the restrictio…

All of the “standard” HTM configurations are based on OOP and are incompatible with what I am doing. Many people here struggle with making a simple encoder to process data sets. I am not ready to support teaching people how to transform data sets into the activation maps that I work with at this time.

Interpreting activation patterns as results is likely to be equally difficult for most HTM users.

So - I don’t have anything that you could build off of at this time. I am working on making the execution kernel and tool set a little less user hostile and writing more theory posts so users will be able to understand what the software is doing and how to use it. I have to admit that much of my work has been code first - comment later, and reading it won’t shed much light on what it is doing. I used to comment more but I keep changing the code as I try things out and the comments got to be totally misleading so I killed lots of then as the comments were actually counter-productive at one point. Such is the joy of trying to cram in a huge project in the few hours between dinner and bed each night. I would fire me if I coded like this at work.

If you are to the point where you could code an HTM from scratch then the theory of how hex-grid coding fits is at the same level as making a spatial pooler. If you don’t feel comfortable making a SP from scratch then this is not something that is likely to be helpful to you.

As far as integrating HTM and DL - you may want to read this post and give it some reflection:

Has anyone tested Numenta on well-known benchmarks?

This question has been asked before. The issue is that HTM does different things than other networks. The comparison that comes to mind is comparing a F1 race car to a dump truck. They both have about the same horsepower engine but they use them in very different ways - one goes very fast and one carries very large loads. DL is very good at mapping one high dimensional space to another. Exploring and mapping these spaces is a long and computationally expensive process. HTM is very powerful i…