Data Drift is the phenomenon where the generating model behind the data changes over time. Due to data drift, any model built on the past training data becomes less relevant and inaccurate over time. Thus, detecting and controlling for data drift is critical in machine learning models. Hierarchical Temporal Memory (HTM) is a machine learning model developed by Jeff Hawkins, inspired by how the human brain processes information. It is a biologically inspired model of memory that is similar in structure to the neocortex, and whose performance is claimed to be comparable to state of the art models in detecting anomalies in time series data. Another unique benefit of HTMs is its independence from training and testing cycle; all the learning takes place online with streaming data and no separate training and testing cycle is required. In sequential learning paradigm, Sequential Probability Ratio Test (SPRT) offers some unique benefit for online learning and inference. This paper proposes a novel hybrid framework combining HTM and SPRT for real-time data drift detection and anomaly identification. Unlike existing data drift methods, our approach eliminates frequent retraining and ensures low false positive rates. HTMs currently work with one dimensional or univariate data. In a second study, we also propose an application of HTM in multidimensional supervised scenario for anomaly detection by combining the outputs of multiple HTM columns, one for each dimension of the data, through a neural network. Experimental evaluations demonstrate that the proposed method outperforms conventional drift detection techniques like the Kolmogorov-Smirnov (KS) test, Wasserstein distance, and Population Stability Index (PSI) in terms of accuracy, adaptability, and computational efficiency. Our experiments also provide insights into optimizing hyperparameters for real-time deployment in domains such as Telecom.

Building Reinforcement Learning (RL) algorithms which are able to adapt to continuously evolving tasks is an open research challenge. One technology that is known to inherently handle such non-stationary input patterns well is Hierarchical Temporal Memory (HTM), a general and biologically plausible computational model for the human neocortex. As the RL paradigm is inspired by human learning, HTM is a natural framework for an RL algorithm supporting non-stationary environments. In this paper, we present HTMRL, the first strictly HTM-based RL algorithm. We empirically and statistically show that HTMRL scales to many states and actions, and demonstrate that HTM's ability for adapting to changing patterns extends to RL. Specifically, HTMRL performs well on a 10-armed bandit after 750 steps, but only needs a third of that to adapt to the bandit suddenly shuffling its arms. HTMRL is the first iteration of a novel RL approach, with the potential of extending to a capable algorithm for Meta-RL.

Deep learning has proved its supremacy in the world of supervised learning, where we clearly define the tasks that need to be accomplished. But, when it comes to unsupervised learning, research using deep learning has either stalled or not even gotten off the ground! There are a few areas of intelligence which our brain executes flawlessly, but we still do not understand how it does so. Because we don't have an answer to the "how", we have not made a lot of progress in these areas. If you liked my previous article on the functioning of the human brain to create machine learning algorithms that solve complex real world problems, you will enjoy this introductory article on Hierarchical Temporal Memory (HTM). I believe this is the closest we have reached to replicating the underlying principles of the human brain. In this article, we will first look at the areas where deep learning is yet to penetrate.

My name is Vincenzo Lomonaco and I'm a Postdoctoral Researcher at the University of Bologna where, in early 2019, I obtained my PhD in computer science working on "Continual Learning with Deep Architectures" in the effort of making current AI systems more autonomous and adaptive. Personally, I've always been fascinated and intrigued by the research insights coming out of the 15 years of Numenta research at the intersection of biological and machine intelligence. Now, as a visiting research scientist at Numenta, I've finally gotten the chance to go through all its fascinating research in much greater detail. I soon realized that, given the broadness of the Numenta research scope (across both neuroscience and computer science), along with the substantial changes made over the years to both the general theory and its algorithmic implementations, it may not be really straightforward to quickly grasp the concepts around them from a pure machine learning perspective. This is why I decided to provide a single-entry-point, easy-to-follow, and reasonably short guide to the HTM algorithm for people who have never been exposed to Numenta research but have a basic machine learning background.

This article is inspired by the research done during studies in the university. Goal of this article is to act as a note and reminder that finding anomalies is not a trivial task (currently). Anomaly detection refers to the task of finding observations that do not conform to the normal, expected behaviour. These observations can be named as anomalies, outliers, novelty, exceptions, surprises in different application domains. The most popular terms that occur most often in literature are anomalies and outliers.

There hasn't been a major breakthrough in algorithms in the last year.

Summary: This is the second in our "Off the Beaten Path" series looking at innovators in machine learning who have elected strategies and methods outside of the mainstream. In this article we look at Numenta's unique approach to scalar prediction and anomaly detection based on their own brain research. Numenta, the machine intelligence company founded in 2005 by Jeff Hawkins of Palm Pilot fame might well be the poster child for'off the beaten path'. More a research laboratory than commercial venture, Hawkins has been pursuing a strong-AI model of computation that will at once directly model the human brain, and as a result be a general purpose solution to all types of machine learning problems. After swimming against the tide of the'narrow' or'weak' AI approaches represented by deep learning's CNNs and RNN/LSTMs his bet is starting to pay off.

Jeff Hawkins, the chief technology officer of Palm, was the founder of Palm Computing, where he invented the PalmPilot, and also the founder of HandSpring, where he invented the Treo. But Palm and creating mobile devices are only a part-time job for Hawkins. His true passion is neuroscience. Now, after many years of research and meditation, he has proposed an all-encompassing theory of the mammalian neocortex. "Hierarchical Temporal Memory" (HTM) claims to explain how our brains discover, infer, and predict patterns in the phenomenal world.

WIRE)--How do our brains learn and understand the world? That question is of paramount importance to both neuroscientists and technologists who want to build intelligent machines. It has been understood for over a hundred years that the inputs and outputs of the brain are constantly changing sequences of patterns and therefore learning and recalling sequences must be a fundamental operation of neurons. Numerous proposals have been made for how neural networks might learn sequences. However, these proposals did not match the anatomy and function observed in the brain.

Numenta's theory of how the brain learns and understands sequences of patterns may be an essential component for creating intelligent machines REDWOOD CITY, CA –April 12, 2016-- How do our brains learn and understand the world? That question is of paramount importance to both neuroscientists and technologists who want to build intelligent machines. It has been understood for over a hundred years that the inputs and outputs of the brain are constantly changing sequences of patterns and therefore learning and recalling sequences must be a fundamental operation of neurons. Numerous proposals have been made for how neural networks might learn sequences. However, these proposals did not match the anatomy and function observed in the brain.