Plausible Algorithm Research Articles

Biological plausible algorithm for seizure detection: Toward AI-enabled electroceuticals at the edge

Nearly 1% of people worldwide suffer from epilepsy. Electroencephalogram (EEG)-based diagnostics and monitoring tools, such as scalp EEG, subscalp EEG, stereo EEG, or sub/epi-dural EEG recordings [also known as electrocorticography (ECoG)], are widely used in different settings as the gold standard techniques to perform seizure identification, localization, and more primarily in epilepsy or suspected epilepsy in patients. Techniques such as subscalp EEG and ECoG offer long-term brain interaction, potentially replacing traditional electroceuticals with smart closed-loop therapies. However, these systems require continuous on-device training due to real-time demands and high power consumption. Inspired by the brain architecture, biologically plausible algorithms, such as some neuromorphic computing, show promise in addressing these challenges. In our research, we utilized liquid time-constant spiking neural networks with forward propagation through time to detect seizures in scalp-EEG. We trained and validated our model on the Temple University Hospital dataset and tested its generalization on out-of-sample data from the Royal Prince Alfred Hospital (RPAH) and EPILEPSIAE datasets. Our model achieved high area under the receiver operating characteristic curve (AUROC) scores of 0.83 in both datasets. We assessed the robustness by decreasing the memory size by 90% and obtained an overall AUROC of 0.82 in the RPAH dataset and 0.83 in the EPILEPSIAE dataset. Our model showed outstanding results of 3.1 μJ power consumption per inference and a 20% firing rate during training. This allows for incorporating bio-inspired efficient algorithms for on-device training, tackling challenges such as memory, power consumption, and efficiency.

Efficient Target Propagation by Deriving Analytical Solution

Exploring biologically plausible algorithms as alternatives to error backpropagation (BP) is a challenging research topic in artificial intelligence. It also provides insights into the brain's learning methods. Recently, when combined with well-designed feedback loss functions such as Local Difference Reconstruction Loss (LDRL) and through hierarchical training of feedback pathway synaptic weights, Target Propagation (TP) has achieved performance comparable to BP in image classification tasks. However, with an increase in the number of network layers, the tuning and training cost of feedback weights escalates. Drawing inspiration from the work of Ernoult et al., we propose a training method that seeks the optimal solution for feedback weights. This method enhances the efficiency of feedback training by analytically minimizing feedback loss, allowing the feedback layer to skip certain local training iterations. More specifically, we introduce the Jacobian matching loss (JML) for feedback training. We also proactively implement layers designed to derive analytical solutions that minimize JML. Through experiments, we have validated the effectiveness of this approach. Using the CIFAR-10 dataset, our method showcases accuracy levels comparable to state-of-the-art TP methods. Furthermore, we have explored its effectiveness in more intricate network architectures.

Fixed-Weight Difference Target Propagation

Target Propagation (TP) is a biologically more plausible algorithm than the error backpropagation (BP) to train deep networks, and improving practicality of TP is an open issue. TP methods require the feedforward and feedback networks to form layer-wise autoencoders for propagating the target values generated at the output layer. However, this causes certain drawbacks; e.g., careful hyperparameter tuning is required to synchronize the feedforward and feedback training, and frequent updates of the feedback path are usually required than that of the feedforward path. Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work? We answer this question by presenting Fixed-Weight Difference Target Propagation (FW-DTP) that keeps the feedback weights constant during training. We confirmed that this simple method, which naturally resolves the abovementioned problems of TP, can still deliver informative target values to hidden layers for a given task; indeed, FW-DTP consistently achieves higher test performance than a baseline, the Difference Target Propagation (DTP), on four classification datasets. We also present a novel propagation architecture that explains the exact form of the feedback function of DTP to analyze FW-DTP. Our code is available at https://github.com/TatsukichiShibuya/Fixed-Weight-Difference-Target-Propagation.

A SURVEY ON AIR WRITING CHARACTER RECOGNITION AND TRANSLATION

Computer systems are increasingly using airwriting recognition since it can be done quickly and intelligently. The term "air-writing acknowledgment apparatus" refers to the use of a stylus to draw an articulated character or expression in free space. This study presents a simple yet effective convolutional neural network-based air-writing recognition method (CNN). It is suggested to use a plausible algorithm tracking hands to reward air-writing circles captured through a web camera. This study provides a straightforward but efficient method for recognizing air-writing that uses deep convolutional neural networks (CNNs). With the aid of hand motions, users can write characters in the air that are subsequently translated into written text using an air writing character recognition and translation technology. Convolutional neural networks (CNN), which are trained to recognise and decipher human hand gestures, power this technology. The device uses a camera to record the hand movements and then runs the data through CNN to identify the characters being typed. The identified characters are then converted into text that may be presented on a screen using text-to-speech technology.

Biologically-inspired neuronal adaptation improves learning in neural networks

ABSTRACT Since humans still outperform artificial neural networks on many tasks, drawing inspiration from the brain may help to improve current machine learning algorithms. Contrastive Hebbian learning (CHL) and equilibrium propagation (EP) are biologically plausible algorithms that update weights using only local information (without explicitly calculating gradients) and still achieve performance comparable to conventional backpropagation. In this study, we augmented CHL and EP with Adjusted Adaptation, inspired by the adaptation effect observed in neurons, in which a neuron’s response to a given stimulus is adjusted after a short time. We add this adaptation feature to multilayer perceptrons and convolutional neural networks trained on MNIST and CIFAR-10. Surprisingly, adaptation improved the performance of these networks. We discuss the biological inspiration for this idea and investigate why Neuronal Adaptation could be an important brain mechanism to improve the stability and accuracy of learning.

A Theoretical Perspective on Hyperdimensional Computing

Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining highdimensional, low-precision, distributed representations of data. These representations can be combined with simple, neurally plausible algorithms to effect a variety of information processing tasks. HD computing has recently garnered significant interest from the computer hardware community as an energy-efficient, low-latency, and noise-robust tool for solving learning problems. In this review, we present a unified treatment of the theoretical foundations of HD computing with a focus on the suitability of representations for learning.

How Intelligence is Understood Today

The article is devoted to understanding the ways of explaining intellectual abilities in the light of new developments in the field of artificial intelligence and discoveries related to the study of complex adaptive animal behavior based on the reward system. The paper reviews the latest advances in the development of biologically plausible learning algorithms, the purpose of which is to explain the large amount of accumulated data from the field of neuroscience. Within the framework of this approach, reinforcement learning algorithms are proposed as the basis for any kind of cognitive activity. Understanding intelligence as a set of flexible adaptive abilities to achieve a goal provides a new conceptual framework for explaining how the brain works at a functional level. The formation of forecasts for the future, the construction of time steps and the existence of an internal assessment system in such systems is psychologically and biologically plausible and can potentially become a new milestone in the study of intelligence.

IMPLEMENTATION POSSIBILITY OF A LIKE DEEP LEARNING ALGORITHMS ON NON-DEEP NETWORKS WITH HIDDEN LAYERS

Learning deep neural networks using the backpropagation algorithm is considered implausible from a biological point of view. Numerous recent publications offer sophisticated models for biologically plausible deep learning options that typically define success as achieving a test accuracy of around 98 % in the MNIST dataset. Here we examine how far we can go in the classification of numbers (MNIST) with biologically plausible rules for learning in a network with one hidden layer and one reading layer. The weights of the hidden layer are either fixed (random or random Gabor filters), or are trained by uncontrolled methods (analysis of main/independent components or sparse coding), which can be implemented in accordance with local training rules. The paper shows that high dimensionality of hidden layers is more important for high performance than global functions retrieved by PCA, ICA, or SC. Tests on the CIFAR10 object recognition problem lead to the same conclusion, indicating that this observation is not entirely problem specific. Unlike biologically plausible deep learning algorithms that are derived from the backpropagation algorithm approximations, we have focused here on shallow networks with only one hidden layer. Globally applied, randomly initialized filters with fixed weights/Gabor coefficients (RP/RGs) of large hidden layers result in better classification performance than training them with unsupervised methods such as principal/independent analysis (PCA/ICA) or sparse coding (SC). Therefore, the conclusion is that uncontrolled training does not lead to better performance than fixed random projections or Gabor filters for large hidden layers.

Imprecise learning and uncertainty.

A study in Nature Human Behaviour proposes a biologically plausible algorithm producing near-optimal behaviour in uncertain and volatile environments through computational imprecision. A complementary study in the same issue shows that, depending on context, uncertainty itself guides different decisions and is differentially represented in the brain.

Application of a Brain-Inspired Spiking Neural Network Architecture to Odor Data Classification.

Existing methods in neuromorphic olfaction mainly focus on implementing the data transformation based on the neurobiological architecture of the olfactory pathway. While the transformation is pivotal for the sparse spike-based representation of odor data, classification techniques based on the bio-computations of the higher brain areas, which process the spiking data for identification of odor, remain largely unexplored. This paper argues that brain-inspired spiking neural networks constitute a promising approach for the next generation of machine intelligence for odor data processing. Inspired by principles of brain information processing, here we propose the first spiking neural network method and associated deep machine learning system for classification of odor data. The paper demonstrates that the proposed approach has several advantages when compared to the current state-of-the-art methods. Based on results obtained using a benchmark dataset, the model achieved a high classification accuracy for a large number of odors and has the capacity for incremental learning on new data. The paper explores different spike encoding algorithms and finds that the most suitable for the task is the step-wise encoding function. Further directions in the brain-inspired study of odor machine classification include investigation of more biologically plausible algorithms for mapping, learning, and interpretation of odor data along with the realization of these algorithms on some highly parallel and low power consuming neuromorphic hardware devices for real-world applications.

Cognitive Template-Clustering Improved LineMod for Efficient Multi-object Pose Estimation

Various types of theoretical algorithms have been proposed for 6D pose estimation, e.g., the point pair method, template matching method, Hough forest method, and deep learning method. However, they are still far from the performance of our natural biological systems, which can undertake 6D pose estimation of multi-objects efficiently, especially with severe occlusion. With the inspiration of the Müller-Lyer illusion in the biological visual system, in this paper, we propose a cognitive template-clustering improved LineMod (CT-LineMod) model. The model uses a 7D cognitive feature vector to replace standard 3D spatial points in the clustering procedure of Patch-LineMod, in which the cognitive distance of different 3D spatial points will be further influenced by the additional 4D information related with direction and magnitude of features in the Müller-Lyer illusion. The 7D vector will be dimensionally reduced into the 3D vector by the gradient-descent method, and then further clustered by K-means to aggregately match templates and automatically eliminate superfluous clusters, which makes the template matching possible on both holistic and part-based scales. The model has been verified on the standard Doumanoglou dataset and demonstrates a state-of-the-art performance, which shows the accuracy and efficiency of the proposed model on cognitive feature distance measurement and template selection on multiple pose estimation under severe occlusion. The powerful feature representation in the biological visual system also includes characteristics of the Müller-Lyer illusion, which, to some extent, will provide guidance towards a biologically plausible algorithm for efficient 6D pose estimation under severe occlusion.

A Novel Adaptive Controller for Robot Manipulators Based on Active Inference

More adaptive controllers for robot manipulators are needed, which can deal with large model uncertainties. This paper presents a novel active inference controller (AIC) as an adaptive control scheme for industrial robots. This scheme is easily scalable to high degrees-of-freedom, and it maintains high performance even in the presence of large unmodeled dynamics. The proposed method is based on active inference, a promising neuroscientific theory of the brain, which describes a biologically plausible algorithm for perception and action. In this work, we formulate active inference from a control perspective, deriving a model-free control law which is less sensitive to unmodeled dynamics. The performance and the adaptive properties of the algorithm are compared to a state-of-the-art model reference adaptive controller (MRAC) in an experimental setup with a real 7-DOF robot arm. The results showed that the AIC outperformed the MRAC in terms of adaptability, providing a more general control law. This confirmed the relevance of active inference for robot control.

Saccade Velocity Driven Oscillatory Network Model of Grid Cells.

Grid cells and place cells are believed to be cellular substrates for the spatial navigation functions of hippocampus as experimental animals physically navigated in 2D and 3D spaces. However, a recent saccade study on head fixated monkey has also reported grid-like representations on saccadic trajectory while the animal scanned the images on a computer screen. We present two computational models that explain the formation of grid patterns on saccadic trajectory formed on the novel Images. The first model named Saccade Velocity Driven Oscillatory Network -Direct PCA (SVDON—DPCA) explains how grid patterns can be generated on saccadic space using Principal Component Analysis (PCA) like learning rule. The model adopts a hierarchical architecture. We extend this to a network model viz. Saccade Velocity Driven Oscillatory Network—Network PCA (SVDON-NPCA) where the direct PCA stage is replaced by a neural network that can implement PCA using a neurally plausible algorithm. This gives the leverage to study the formation of grid cells at a network level. Saccade trajectory for both models is generated based on an attention model which attends to the salient location by computing the saliency maps of the images. Both models capture the spatial characteristics of grid cells such as grid scale variation on the dorso-ventral axis of Medial Entorhinal cortex. Adding one more layer of LAHN over the SVDON-NPCA model predicts the Place cells in saccadic space, which are yet to be discovered experimentally. To the best of our knowledge, this is the first attempt to model grid cells and place cells from saccade trajectory.

Phosphors Based on Phosphates of NaZr2(PO4)3 and Langbeinite Structural Families

The review covers aspects of modeling the composition and luminescent properties of phosphates of NaZr2(PO4)3 (NZP) and langbeinite structural families. Based on the analysis of phosphates structure, a plausible algorithm of the use of crystal chemistry data for modeling compositions, structure, and properties of new compounds is proposed. The following properties determined by requirements to materials for the chosen purposes are studied: behavior on heating and in water systems, luminescence, and biocompatibility. Prospects for the use of such data for solving various problems of materials science, LED technologies, bioimaging, and X-ray induced photodynamic therapy of oncological diseases are shown.

A computational model of mapping in echolocating bats

Echolocating bats can navigate to salient places relying solely on their sonar system. Currently, much about the mechanism underlying sonar-based navigation in bats remains unknown, and no computational models of this ability have been proposed. In this paper, we propose a computational model of sonar-based navigation in bats. In particular, we advance a model explaining how bats could assemble a cognitive map from their environment using only their sonar readings. The model consists of two loops. The first loop performs low-level obstacle avoidance. This gives rise to stable and environment-derived flight corridors (i.e. preferred pathways for bats flying through the environment). The second high-level loop runs on top of the low-level loop and performs mapping. Mapping is done by combining local view information extracted from echo signals with local self-motion information to recognize previously visited places and memorize their spatial relationships. Using this model, we simulate a bat exploring unstructured environments while constructing a cognitive map using a biologically plausible algorithm. The model we propose allows the simulated bat to construct a global map of its flight paths through the environment without the bat ever reconstructing the three-dimensional layout of the local environment from any of its received echo signals. Indeed, neither the obstacle avoidance strategy that guides the bat through space nor the mapping algorithm requires the three-dimensional geometric structure of the environment to be accessible to the bat.

Modelling the spread of innovation in wild birds.

We apply three plausible algorithms in agent-based computer simulations to recent experiments on social learning in wild birds. Although some of the phenomena are simulated by all three learning algorithms, several manifestations of social conformity bias are simulated by only the approximate majority (AM) algorithm, which has roots in chemistry, molecular biology and theoretical computer science. The simulations generate testable predictions and provide several explanatory insights into the diffusion of innovation through a population. The AM algorithm's success raises the possibility of its usefulness in studying group dynamics more generally, in several different scientific domains. Our differential-equation model matches simulation results and provides mathematical insights into the dynamics of these algorithms.

Hierarchical Bayesian models of cognitive development.

This article provides an introductory overview of the state of research on Hierarchical Bayesian Modeling in cognitive development. First, a brief historical summary and a definition of hierarchies in Bayesian modeling are given. Subsequently, some model structures are described based on four examples in the literature. These are models for the development of the shape bias, for learning ontological kinds and causal schemata as well as for the categorization of objects. The Bayesian modeling approach is then compared with the connectionist and nativist modeling paradigms and considered in view of Marr's (1982) three description levels of information-processing mechanisms. In this context, psychologically plausible algorithms and ideas of their neural implementation are presented. In addition to criticism and limitations of the approach, research needs are identified.

Neuronal Maximum a Posteriori Estimation on Microelectrode Arrays

Neuronal Maximum a Posteriori Estimation on Microelectrode Arrays

Detection of radio signals that appear and disappear at unknown moments

The most plausible algorithm for the detection of a radio signal with unknown amplitude, phase and the moments of appearance and disappearance is synthesized. A two-channel quasi-optimal detector of radio signal the structure of which is simpler than the structure of the optimal detector is proposed. Asymptotic characteristics of the quasi-optimal detector are determined.

A spiking neural network model of model-free reinforcement learning with high-dimensional sensory input and perceptual ambiguity.

A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach.