by David Rawlinson and Gideon Kowadlo
Regions communicate with other, nearby regions in the same level of the hierarchy. Regions also communicate with a few regions in a higher level of the hierarchy, and a few regions in a lower level of the hierarchy. Notionally, abstraction increases as you move towards higher levels in the hierarchy. Note that Hawkins and Blakeslee define abstraction as “the accumulation of invariances”.
Levels and Layers
Newcomers to MPF/CLA/HTM theory sometimes confuse “cortical layers” and connections between regions placed in different “levels” of the hierarchy. We recommend everyone uses layers to talk about cortical layers and levels to talk about hierarchy levels, although the levels and layers are somewhat synonymous in English. I believe this confusion arises because readers expect to learn one new concept at a time, but in fact levels and layers are two separate things.
There are several distinct routes that information takes through the hierarchy. Each route is called a “pathway”. What is a pathway? In short, a pathway is a set of assumptions that allows us to make some broad statements about what components are connected, and how. We assume that the content of data in each pathway is qualitatively different. We also assume there is limited mixing of data between pathways, except where some function is performed to specifically combine the data.
There are two directions that have meaning within the MPF/CLA/HTM literature. These are feed-forward and feed-back. Feed-Forward (FF) means data travelling UP between hierarchy levels, towards increasing abstraction. Feed-Back (FB) means data travelling DOWN between hierarchy levels, with reducing abstraction and taking on more concrete forms closer to raw inputs.
Conceptual Region Architecture
MPF/CLA/HTM broadly outlines the architecture of each Region as follows. Each region has a handful of distinct functional components, namely: Spatial Pooler, Sequence Memory, and Temporal Pooler. Prediction is also a core feature of each Region, though it may not be considered a separate component. I believe that Hawkins would not consider this to be a complete list, as the CLA algorithm is still being developed and does not yet cover all cortical functions. Note that the conceptual entities described here do not imply structural boundaries or say anything about how this might look as a neural network.
The Spatial Pooler identifies common patterns in the FF direct input and replaces them with activation of a single cell (or, variable, or state, or label, depending on your preferred terminology). The spatial pooler is functioning as an unsupervised classifier to transform input patterns into abstract labels that represent specific patterns.
The FF direct pathway cannot be driven by feedback from higher levels alone: FF input is always needed to fully activate cells in the Sequence Memory. As a hierarchy of unsupervised classifiers, the FF pathways are similar to the Deep Learning hierarchy.
Prediction is specifically a process of activating Sequence Memory cells that represent FF input patterns that are likely to occur in the near future. Prediction changes Sequence Memory cells to a receptive state where they are more easily activated by future FF input. In this way, prediction makes classification of FF input more accurate. Improvement is due to the extra information provided by prediction, using both the history of Sequence Cell activation within the region and the history of activation of Sequence Memory cells within higher regions, the latter via the FB pathway.
It is probable that the FB pathway contains prediction data, possibly in addition to Sequence Memory cell state. This is described in MPF/HTM literature, but is not specifically encoded in existing CLA documentation.
Personally, I believe that prediction is synonymous with the generation of behaviour and that it has dual purposes; firstly, to enable regions to better understand future FF input, and secondly, to produce useful actions. A future article will discuss the topic of whether prediction and planning actions could be the same thing in the brain’s internal representation. An indirect FB pathway is not shown in this diagram because it is not described in MPF/CLA literature.
While Spatial Pooling tries to replace instantaneous input patterns with labels, Temporal pooling attempts to simplify changes over time by replacing common sequences with labels. This is a function not explicitly handled in Deep Learning methods, which are typically applied to static data. MPF/CLA/HTM is explicitly designed to handle a continuous stream of varying input.
Temporal pooling ensures that regions at higher levels in the hierarchy encode longer sequences of patterns, allowing the hierarchy to recognise long-term causes and effects. The input data for every region is different, ensuring that each region produces unique representations of different sub-problems. Spatial and Temporal pooling, plus the merging of multiple lower regions in a tree-like structure, all contribute to the uniqueness of each region’s Sequence Memory representation.
Numenta also claim that there is a timing function in cortical prediction, that enables the region to know when specific cells will be driven active by FF input. Since this function is speculative, it is not shown in the diagram above. The timing function is reportedly due to cortical layer 5.
Mapping Region Architecture to Cortical Layers
To try to present a clear picture of their stance, I have included a graphic (below) showing the functions of each biological cortex layer as defined by CLA. The graphic also shows the flows of data both between layers and between regions. Note that the flows given here are only those as described in the CLA white paper and Hawkins’ new ideas on temporal pooling. Other sources do describe additional/alternative connections between cortical levels and regions. The exact interactions of each layer of neurons are somewhat messy and difficult to interpret.
I hope this review of the terminology and architecture is helpful. Although the MPF/CLA/HTM framework is thoroughly and consistently documented, some of the details and concepts can be hard to picture, especially in the first encounter. The CLA White Paper does a good job of explaining Sparse Distributed Representations and spatial, temporal pooler implementations as biologically-inspired Sequence Memory cells. However, the grosser features of the posited hierarchy are not so thoroughly described.
It is worth noting that according to recent discussions on the NUPIC mailing list, the current NUPIC implementation of CLA does not correctly support multi-level hierarchies correctly. This problem is expected to be addressed in 2014, permitting multi-level hierarchies.
Thanks very much, David and Gideon! This has cleared a few things up for me. Are you aware of any major developments/insights by Numenta or others (including yourselves) since you wrote this article? Are there any parts of this article that are now known to be incorrect or that have been supported by more evidence? Thanks!
Hi Joseph thanks for your comment. This article is pretty old… we are currently writing a new series summarizing everything we have learnt and find relevant. So far it's mostly the bio side but algorithms part is coming soon.
Have a look at :
Keep watching for the next post in the series which will try to interpret all this from a computational perspective. We're pretty excited about that one. It's already drafted but being reviewed internally.
Regarding the algorithm insights, we have spent some time looking at temporal sequences – LSTMs and Predictive Coding particularly. The approach used in Numenta's HTM is Temporal Slowness. We prefer Predictive Coding but these are both ways to implement Temporal Pooling.
Thanks very much, Dave. I'll get reading!