Cortical Learning Algorithm Research Articles

Adaptive action-prediction cortical learning algorithm under uncertain environments

The cortical learning algorithm (CLA) is a time series prediction algorithm. Memory elements called columns and cells discretely represent data with their state combinations, whereas linking elements called synapses change their state combinations. For tasks requiring to take actions, the action-prediction CLA (ACLA) has an advantage to complement missing state values with their predictions. However, an increase in the number of missing state values (i) generates excess synapses negatively affect the action predictions and (ii) decreases the stability of data representation and makes the output of action values difficult. This paper proposes an adaptive ACLA using (i) adaptive synapse adjustment and (ii) adaptive action-separated decoding in an uncertain environment, missing multiple input state values probabilistically. (i) The proposed adaptive synapse adjustment suppresses unnecessary synapses. (ii) The proposed adaptive action-separated decoding adaptively outputs an action prediction separately for each action value. Experimental results using uncertain two- and three-dimensional mountain car tasks show that the proposed adaptive ACLA achieves a more robust action prediction performance than the conventional ACLA, DDPG, and the three LSTM-assisted reinforcement learning algorithms of DDPG, TD3, and SAC, even though the number of missing state values and their frequencies increase. These results implicate that the proposed adaptive ACLA is a way to making decisions for the future, even in cases where information surrounding the situation partially lacked.

Multilayered Cortical Learning Algorithm for Forecasting Time-Series Data with Probabilistically Changing Trends

Multilayered Cortical Learning Algorithm for Forecasting Time-Series Data with Probabilistically Changing Trends

Congratulations ! JACIII Best Paper and Young Researcher Awards 2021

We are pleased to announce that the JACIII Awards of 2021 have been decided by the JACIII editorial boards. This year, the award winning papers were severely and fairly selected among 362 papers published in JACIII Vols. 22 (2018) to 24 (2020) and there was no entries that deserved the Best Review Paper award. The award ceremony was held online in order to prevent spreading of COVID-19. JACIII BEST PAPER AWARD 2021 Sotetsu Suzugamine, Takeru Aoki, Keiki Takadama, and Hiroyuki Sato Self-Structured Cortical Learning Algorithm by Dynamically Adjusting Columns and Cells JACIII Vol.24 No.2, pp. 185-198, 2020. JACIII YOUNG RESEARCHER AWARD 2021 JACIII YOUNG RESEARCHER AWARD 2021 Xiaobo Liu Jinxin Chi Emotion Recognition Based on Multi-Composition Deep Forest and Transferred Convolutional Neural Network Object-Oriented 3D Semantic Mapping Based on Instance Segmentation By Xiaobo Liu, Xu Yin, Min Wang, Yaoming Cai, and Guang Qi By Jinxin Chi, Hao Wu, and Guohui Tian JACIII Vol.23 No.5, pp. 883-890, 2019. JACIII Vol.23 No.4, pp. 695-704, 2019.

Adaptive Synapse Arrangement in Cortical Learning Algorithm

The cortical learning algorithm (CLA) is a time-series data prediction method that is designed based on the human neocortex. The CLA has multiple columns that are associated with the input data bits by synapses. The input data is then converted into an internal column representation based on the synapse relation. Because the synapse relation between the columns and input data bits is fixed during the entire prediction process in the conventional CLA, it cannot adapt to input data biases. Consequently, columns not used for internal representations arise, resulting in a low prediction accuracy in the conventional CLA. To improve the prediction accuracy of the CLA, we propose a CLA that self-adaptively arranges the column synapses according to the input data tendencies and verify its effectiveness with several artificial time-series data and real-world electricity load prediction data from New York City. Experimental results show that the proposed CLA achieves higher prediction accuracy than the conventional CLA and LSTMs with different network optimization algorithms by arranging column synapses according to the input data tendency.

A Scalable Cluster-based Hierarchical Hardware Accelerator for a Cortically Inspired Algorithm

This article describes a scalable, configurable and cluster-based hierarchical hardware accelerator through custom hardware architecture for Sparsey, a cortical learning algorithm. Sparsey is inspired by the operation of the human cortex and uses a Sparse Distributed Representation to enable unsupervised learning and inference in the same algorithm. A distributed on-chip memory organization is designed and implemented in custom hardware to improve memory bandwidth and accelerate the memory read/write operations for synaptic weight matrices. Bit-level data are processed from distributed on-chip memory and custom multiply-accumulate hardware is implemented for binary and fixed-point multiply-accumulation operations. The fixed-point arithmetic and fixed-point storage are also adapted in this implementation. At 16 nm, the custom hardware of Sparsey achieved an overall 24.39× speedup, 353.12× energy efficiency per frame, and 1.43× reduction in silicon area against a state-of-the-art GPU.

A novel model based on Sequential Adaptive Memory for English–Hindi Translation

Machine-based language translation has been certainly picking up. Still, machines lag behind the cognitive powers of human beings. Neural Machine Translation (NMT) methods require huge datasets and computational power for high-quality translation. A novel Sequential Adaptive Memory (SAM) cognitive model-based machine translation system for English to Hindi translation, was proposed. This model is an augmented version of the Cortical Learning Algorithm (CLA). The SAM is based on the architecture of the neocortex region of the brain, where speech and language comprehension and production take place. The proposed model is capable of learning with smaller datasets. This model employs the sequence to sequence learning approach, which provides better quality translation. It enables the creation of word pairs, dictionaries, and rules for translation. The results of the proposed approach are compared with the traditional phrase-based SMT approach as well as with the state-of-the-art NMT approach. The results are comparable with the results of the conventional approaches. We illustrate that the limitations of the approaches are won over by the proposed SAM approach. It is observed that SAM is capable of exhibiting satisfactory quality translation for low resource languages as well.

A Robot Obstacle Avoidance Method based on Random Forest HTM Cortical Learning Algorithm

Robotics mainly concern with the movement of robot with improvement obstacle avoidance, this issue is handed. It contains of a Microcontroller to process the data, and Ultrasonic sensors to detect the obstacles on its path. Artificial intelligence is used to predict the presence of obstacle in the path. In this research random forest algorithm is used and it is improved by RFHTMC algorithm. Deep learning mainly compromises of reducing the mean absolute error of forecasting. Problem with random forest is time complexity, as it involves formation of many classification trees. The proposed algorithm reduces the set of rules which is used for classification model, to improve time complexity. Performance analysis shows an significant improvement in results as compare to other deep learning algorithm as well as random forest. Forecasting accuracy shows 8% improvement as compare to random forest with 26% reduced operation time.

Scaling the HTM Spatial Pooler

The Hierarchical Temporal Memory Cortical Learning Algorithm (HTM CLA) is a theory and machine learning technology that aims to capture cortical algorithm of the neocortex. Inspired by the biological functioning of the neocortex, it provides a theoretical framework, which helps to better understand how the cortical algorithm inside of the brain might work. It organizes populations of neurons in column-like units, crossing several layers such that the units are connected into structures called regions (areas). Areas and columns are hierarchically organized and can further be connected into more complex networks, which implement higher cognitive capabilities like invariant representations. Columns inside of layers are specialized on learning of spatial patterns and sequences. This work targets specifically spatial pattern learning algorithm called Spatial Pooler. A complex topology and high number of neurons used in this algorithm, require more computing power than even a single machine with multiple cores or a GPUs could provide. This work aims to improve the HTM CLA Spatial Pooler by enabling it to run in the distributed environment on multiple physical machines by using the Actor Programming Model. The proposed model is based on a mathematical theory and computation model, which targets massive concurrency. Using this model drives different reasoning about concurrent execution and enables flexible distribution of parallel cortical computation logic across multiple physical nodes. This work is the first one about the parallel HTM Spatial Pooler on multiple physical nodes with named computational model. With the increasing popularity of cloud computing and server less architectures, it is the first step towards proposing interconnected independent HTM CLA units in an elastic cognitive network. Thereby it can provide an alternative to deep neuronal networks, with theoretically unlimited scale in a distributed cloud environment.

Self-Structured Cortical Learning Algorithm by Dynamically Adjusting Columns and Cells

The cortical learning algorithm (CLA) is a type of time-series data prediction algorithm based on the human neocortex. CLA uses multiple columns to represent an input data value at a timestep, and each column has multiple cells to represent the time-series context of the input data. In the conventional CLA, the numbers of columns and cells are user-defined parameters. These parameters depend on the input data, which can be unknown before learning. To avoid the necessity for setting these parameters beforehand, in this work, we propose a self-structured CLA that dynamically adjusts the numbers of columns and cells according to the input data. The experimental results using the time-series test inputs of a sine wave, combined sine wave, and logistic map data demonstrate that the proposed self-structured algorithm can dynamically adjust the numbers of columns and cells depending on the input data. Moreover, the prediction accuracy is higher than those of the conventional long short-term memory and CLAs with various fixed numbers of columns and cells. Furthermore, the experimental results on a multistep prediction of real-world power consumption show that the proposed self-structured CLA achieves a higher prediction accuracy than the conventional long short-term memory.

CLASSIC: A cortex-inspired hardware accelerator

This work explores the feasibility of specialized hardware implementing the Cortical Learning Algorithm (CLA) in order to fully exploit its inherent advantages. This algorithm, which is inspired by the current understanding of the mammalian neo-cortex, is the basis of the Hierarchical Temporal Memory (HTM). In contrast to other machine learning (ML) approaches, the structure is not application dependent and relies on fully unsupervised continuous learning. We hypothesize that a hardware implementation will be able not only to extend the existing practical uses of these ideas to broader scenarios but also to exploit CLA’s hardware-friendly characteristics.The architecture proposed will enable the system size to be scaled up compared to a state-of-the-art CLA software implementation. It may be possible to improve performance by 4 orders of magnitude and energy efficiency by up to 8 orders of magnitude.Given the problem’s complex nature, we found that the most demanding issue, from a scalability standpoint, is the massive degree of connectivity required. We propose to use a packet-switched network to tackle this. The paper addresses the fundamental issues of such an approach, proposing solutions to achieve a scalable proposal. We will analyze cost and performance when using well-known architectural techniques and tools. The results obtained suggest that even with CMOS technology, under constrained cost, it might be possible to implement a large-scale system. We found that the proposed solutions enable a saving of ∼90% of the original communication costs running either synthetic or realistic workloads.

Evaluating Machine Learning Techniques for Activity Classification in Smart Home Environments

With the widespread adoption of the Internet-connected devices, and with the prevalence of the Internet of Things (IoT) applications, there is an increased interest in machine learning techniques that can provide useful and interesting services in the smart home domain. The areas that machine learning techniques can help advance are varied and ever-evolving. Classifying smart home inhabitants’ Activities of Daily Living (ADLs), is one prominent example. The ability of machine learning technique to find meaningful spatio-temporal relations of high-dimensional data is an important requirement as well. This paper presents a comparative evaluation of state-of-the-art machine learning techniques to classify ADLs in the smart home domain. Forty-two synthetic datasets and two real-world datasets with multiple inhabitants are used to evaluate and compare the performance of the identified machine learning techniques. Our results show significant performance differences between the evaluated techniques. Such as AdaBoost, Cortical Learning Algorithm (CLA), Decision Trees, Hidden Markov Model (HMM), Multi-layer Perceptron (MLP), Structured Perceptron and Support Vector Machines (SVM). Overall, neural network based techniques have shown superiority over the other tested techniques.

A Novel Machine Learning Approach to Credit Card Fraud Detection

The use of credit cards is of paramount importance in improving the economic strength of any nation, however, fraudulent activities associated with it is of great concern. When fraud occurs on credit cards, the negative impact is huge as the financial loss experienced cuts across all the parties involved. This paper provides a proactive measure at detecting fraudulent activities regarding the credit card. A novel approach in machine learning known as the cortical learning algorithm was adopted to build the credit card fraud detection model. The algorithm worked on the credit card data obtained from the UCI Repository, it converted the highly populated data to a sparse representation, and then used its learning columns to learn spatial and temporal patterns. The object oriented analysis and design methodology was used in the design of the system which was implemented with JAVA programming language. The simulation was carried out with Matlab. The resulting model performed online learning and recorded higher percentage accuracy of 91% and beyond in detecting fraudulent transactions as compared to the Neural Network model that recorded 89.6%, hence, cases of misclassification was reduced to the barest minimum and efficiency of fraud detection was increased.