NumSharp Cheat Sheet

NumPy to NumSharp Cheat Sheet

Recently, I published a small example project to utilize the htm.core AI algorithm by consuming its REST API via C#. As the API also transfers serialized multi-dimensional NumPy arrays, I was looking for an easy way to get them back into C# objects. I’ve tried out a couple of approaches and finally decided on using the NumSharp library, as I wanted a solution that works on multiple platforms.

I find DataCamps’ Data Science Cheat Sheets very useful and was hoping to find something similar for NumSharp. Well, I didn’t, but obviously that gave me a … more

.NET for Apache Spark Docker Image available on GitHub

.NET for Apache Spark Docker Image available on GitHub

I am really honored by the fact, that a lot of people seem to use my .NET for Apache Spark docker image to explore how C# and Apache Spark can work together, for example.

Additionally, I am getting a lot of request lately, asking whether I would be willing to share the code for creating the images.

And finally, after tidying it up a bit (e.g. removing the experimental Windows support), it is now available on GitHub.

So thanks to everyone who made this image such a success and of course you are very welcome to … more

.NET for Apache Spark 0.11.0 docker image

My .NET for Apache Spark v0.11.0 docker image is now available

.NET for Apache Spark 0.11.0 is now available and I have also updated my related docker images for Linux and Windows on the docker hub.

If you are interested, check out the official resources, or one of the following articles.

more

htm.core parameters – High Order Sequence Memory

In part 2, I used htm.core as a single order sequence memory by allowing only one cell per mini-column. In this post I’ll finally have a first look at the high order sequence memory.

Before we do that, I want to show you one last single order memory example however.

Single Order Sequence Memory Recap

As you might remember from the last post, these were the settings for our htm.core temporal memory (aka sequence memory).

    columns = 8
    inputSDR = SDR( columns )
    cellsPerColumn = 1
    tm = TM(columnDimensions          = (inputSDR.size,),
            cellsPerColumn            = cellsPerColumn,     
more

htm.core parameters – Single Order Sequence Memory

To allow the htm.core temporal memory to learn sequences effectively, it is import to understand the impact of the different parameters in more detail.

In this part I will introduce

  • columnDimensions
  • cellsPerColumn
  • maxSegmentsPerCell
  • maxSynapsesPerSegment
  • initialPermanence
  • connectedPermanence
  • permanenceIncrement
  • predictedSegmentDecrement

Temporal Memory – Previously on this blog…

Part 1 just covered enough basics of htm.core to get us started, and we actually saw how the single order memory got trained.
A cycle of encoded increasing numbers from 0 to 9 was very easy to predict, as there was always just one specific value that could follow the … more

Scroll to top