AND THE WINNER IS .......the paper entitled: "Improved HTM Spatial Pooler with Homeostatic Plasticity control" and written by Damir Dobric, my collegue, CEO and Lead Architect @DAENET. This paper got the Best Industrial Paper Award Certificate! This happened last week at the 10th international conference for pattern recognition and models (ICPRAM 2021) in Vienna in the category machine learning theory and models.

Neuroscience and computational intelligence

With the rapid growth and huge popularity of cloud computing and Machine Learning, it is the first step towards proposing interconnected independent Hirarchical Temporal Memory (HTM) CLA units in an elastic cognitive network. In this case HTM provides a theoretical framework and helps us to better understand how the cortical algorithm inside of the brain might work. The motivation is to discover how the (human) intelligence works and how to put it into the code in a kind of computational intelligence.

Inspiring Neocortex

Inspired by the fantastic area of neurosciences and computational intelligence my collegue Damir Dobric made this research work. He has always been excited by the biological functioning of the neocortex, which provides a theoretical framework and helps us to better understand how the cortical algorithm inside of the brain might work. In his research he has been analyzing the structure of neocortex and to reproduce it into codes.
His concrete point and idea is to reverse-engineer the neocortex: How does human intelligence work like? What is the consequence for computational intelligence and codings? Possibly there is much less relation between ML/AI and maths than biology and neuroscience.

Artificial Intelligence - the disruptive technology

We encounter the technology of the 21st century in almost all areas of everyday life and often support us without our even being aware of it. It is a key digitization technology with enormous opportunities. But immediately after the enthusiasm, concerns arise that AI may be the last invention of mankind. In reality, however, the picture is different. Artificial intelligence is THE disruptive technology of our time.

Please find the Award Winning Paper here: https://www.insticc.org/node/TechnicalProgram/icpram/2021/presentationDetails/103142
References: https://developers.de/2021/02/11/ai-vnext-reverse-engineering-the-neocortex/

Did you already register for the #ICPRAM 2021? The International Conference on Pattern Recognition Applications and Methods will take place via zoom. On February 4th 11:45 Damir Dobric will talk about new Machine Learning Methods, e.g. Hierarchical Temporal Memory. Highly recommended!
Online Registration already started: https://www.insticc.org/node/TechnicalProgram/icpram/2021/presentationDetails/103142
Hierarchical Temporal Memory (HTM) - Spatial Pooler (SP) is a Learning Algorithm for learning of spatial patterns inspired by the neo-cortex. It is designed to learn the pattern in a few iteration steps and to generate the Sparse Distributed Representation (SDR) of the input. It encodes spatially similar inputs into the same or similar SDRs memorized as a population of active neurons organized in groups called micro-columns. Findings in this research show that produced SDRs can be forgotten during the training progress, which causes the SP to learn the same pattern again and converts into the new SDR. This work shows that instable learning behaviour of the SP is caused by the internal boosting algorithm inspired by the homeostatic plasticity mechanism. Previous findings in neurosciences show that this mechanism is only active during the development of new-born mammals and later deactivated or shifted from cortical layer L4, where the SP is supposed to be active. The same mechanism was used in this work. The SP algorithm was extended with the new homeostatic plasticity component that controls the boosting and deactivates it after entering the stable state. Results show that learned SDRs keeps more stable during the lifetime of the Spatial Pooler.