Brain-inspired System Research Articles

Brain-inspired sensorimotor echolocation system for confident landmark recognition.

A landmark is a familiar target in terms of the echoes that it can produce and is important for echolocation-based navigation by bats, robots, and blind humans. A brain-inspired system (BIS) achieves confident recognition, defined as classification to an arbitrarily small error probability (PE), by employing a voting process with an echo sequence. The BIS contains sensory neurons implemented with binary single-layer perceptrons trained to classify echo spectrograms with PE and generate excitatory and inhibitory votes in face neurons until a landmark-specific face neuron achieves recognition by reaching a confidence vote level (CVL). A discrete random step process models the vote count to show the recognition probability can achieve any desired accuracy by decreasing PE or increasing CVL. A hierarchical approach first classifies surface reflector and volume scatterer target categories and then uses that result to classify two subcategories that form four landmarks. The BIS models blind human echolocation to recognize four human-made and foliage landmarks by acquiring suitably sized and dense audible echo sequences. The sensorimotor BIS employs landmark-specific CVL values and a 2.7° view increment to acquire echo sequences that achieve zero-error recognition of each landmark independent of the initial view.

Using a Brain-Inspired Decision-Making System to Model a Real-Time Responsive Risk Assessment of the Dynamic Tasks Involved with Hazardous Materials

Risk assessment of the operations utilized in processing products and services always deals with uncertainties and complexities. The ever-evolving complex and dynamic circumstances make it very difficult to identify and analyze potential events affecting workers’ safety and health. Our first study was on managing the risky situations of a dynamic environment, the transport and storage of residual hazardous materials with high variation in operational times. It showed that the dynamicity of operational functions has a direct relation to the risk of accidents and suggested that such environments require a system to decide whether to perform each new action on a suspected risk condition or not. A practical framework, engaged close to the variable functions involved in potential events, is needed to provide reliable measures for risk assessment. Based on these measures, this framework would help to make decisions at the right time and to take preventive actions. It would support the decision-making process by recognizing the risk-associated features of available information and offer continuously updated alternatives for appropriate actions to prevent unsafe operations. In our second study, we developed a brain-inspired decision-making system for the real-time configuration of dynamic environments. That decision-making system builds knowledge from the least to the most similarities between experienced states to determine the most appropriate action(s) to rapidly reorient risky operations to a safe condition. This paper aims to verify the second study’s proposed system performance in the simulated environment discussed in our first study on residual hazardous materials transportation. We extract information, including the effective factors, from that first study and use it in the decision-making system to prevent risky transportation. This model would be useful in daily risk management as a practical framework for establishing safe operations in today’s industrial environments that involve dangerous chemical or radioactive products.

GrapHD: Graph-Based Hyperdimensional Memorization for Brain-Like Cognitive Learning.

Memorization is an essential functionality that enables today's machine learning algorithms to provide a high quality of learning and reasoning for each prediction. Memorization gives algorithms prior knowledge to keep the context and define confidence for their decision. Unfortunately, the existing deep learning algorithms have a weak and nontransparent notion of memorization. Brain-inspired HyperDimensional Computing (HDC) is introduced as a model of human memory. Therefore, it mimics several important functionalities of the brain memory by operating with a vector that is computationally tractable and mathematically rigorous in describing human cognition. In this manuscript, we introduce a brain-inspired system that represents HDC memorization capability over a graph of relations. We propose GrapHD, hyperdimensional memorization that represents graph-based information in high-dimensional space. GrapHD defines an encoding method representing complex graph structure while supporting both weighted and unweighted graphs. Our encoder spreads the information of all nodes and edges across into a full holistic representation so that no component is more responsible for storing any piece of information than another. Then, GrapHD defines several important cognitive functionalities over the encoded memory graph. These operations include memory reconstruction, information retrieval, graph matching, and shortest path. Our extensive evaluation shows that GrapHD: (1) significantly enhances learning capability by giving the notion of short/long term memorization to learning algorithms, (2) enables cognitive computing and reasoning over memorization graph, and (3) enables holographic brain-like computation with substantial robustness to noise and failure.

A Positioning Method Based on Place Cells and Head-Direction Cells for Inertial/Visual Brain-Inspired Navigation System.

Mammals rely on vision and self-motion information in nature to distinguish directions and navigate accurately and stably. Inspired by the mammalian brain neurons to represent the spatial environment, the brain-inspired positioning method based on multi-sensors’ input is proposed to solve the problem of accurate navigation in the absence of satellite signals. In the research related to the application of brain-inspired engineering, it is not common to fuse various sensor information to improve positioning accuracy and decode navigation parameters from the encoded information of the brain-inspired model. Therefore, this paper establishes the head-direction cell model and the place cell model with application potential based on continuous attractor neural networks (CANNs) to encode visual and inertial input information, and then decodes the direction and position according to the population neuron firing response. The experimental results confirm that the brain-inspired navigation model integrates a variety of information, outputs more accurate and stable navigation parameters, and generates motion paths. The proposed model promotes the effective development of brain-inspired navigation research.

A Brain-Inspired Dynamic Environmental Emergency Response Framework for Sudden Water Pollution Accidents

Sudden water pollution accidents happen frequently in China, and the number of treated accidents is low, due to the slow response speed. In addition, there is a lack of decision support systems that can follow up the whole process instead of just giving a one-time method. This study constructs a framework suitable for China that has both the ability of quick responses and full-time dynamic decision support, such as an experienced expert, while not being affected by pressure, to be used an emergency response for sudden water pollution accidents. To allow new decisionmakers to integrate into this professional decision-making role more quickly, a brain-inspired system is realized through combining the machine learning algorithm KNN and the idea of iteration and dynamic programming. The feasibility of our framework is further tested through a major water pollution happened recently. The results show that this framework can be well connected with the emergency response technology system that has been completed before, while also supporting the rapid and robust decision making such as the decisionmaker’s second brain, reducing the demand for professional background and experience of emergency decisionmakers, thus effectively shorten the waiting period for response.

A brain-inspired localization system for the UAV based on navigation cells

Purpose To solve problems of low intelligence and poor robustness of traditional navigation systems, the purpose of this paper is to propose a brain-inspired localization method of the unmanned aerial vehicle (UAV). Design/methodology/approach First, the yaw angle of the UAV is obtained by modeling head direction cells with one-dimension continuous attractor neural network (1 D-CANN) and then inputs into 3D grid cells. After that, the motion information of the UAV is encoded as the firing of 3 D grid cells using 3 D-CANN. Finally, the current position of the UAV can be decoded from the neuron firing through the period-adic method. Findings Simulation results suggest that continuous yaw and position information can be generated from the conjunctive model of head direction cells and grid cells. Originality/value The proposed period-adic cell decoding method can provide a UAV with the 3 D position, which is more intelligent and robust than traditional navigation methods.

Avalanches and edge-of-chaos learning in neuromorphic nanowire networks

The brain’s efficient information processing is enabled by the interplay between its neuro-synaptic elements and complex network structure. This work reports on the neuromorphic dynamics of nanowire networks (NWNs), a unique brain-inspired system with synapse-like memristive junctions embedded within a recurrent neural network-like structure. Simulation and experiment elucidate how collective memristive switching gives rise to long-range transport pathways, drastically altering the network’s global state via a discontinuous phase transition. The spatio-temporal properties of switching dynamics are found to be consistent with avalanches displaying power-law size and life-time distributions, with exponents obeying the crackling noise relationship, thus satisfying criteria for criticality, as observed in cortical neuronal cultures. Furthermore, NWNs adaptively respond to time varying stimuli, exhibiting diverse dynamics tunable from order to chaos. Dynamical states at the edge-of-chaos are found to optimise information processing for increasingly complex learning tasks. Overall, these results reveal a rich repertoire of emergent, collective neural-like dynamics in NWNs, thus demonstrating the potential for a neuromorphic advantage in information processing.

The Self-Motion Information Response Model in Brain-Inspired Navigation

Grid cells are important neurons related to spatial cognition and navigation in the animal brain and can respond to both external information and self-motion information. The existing models simulated these two types of responses separately, but how to simultaneously develop the two types of connection to respond to the different information has not been simulated. In this paper, first, we develop the connections from place cells to grid cells through improved nonnegative principal component analysis. Then, we construct a continuous attractor network model and an autoencoder network model of grid cell module and convert the parameter learning in the continuous attractor network into weight learning in the autoencoder network. Through parameter learning, the continuous attractor network model can spontaneously generate a hexagonal firing pattern. Ultimately, the grid cell firing fields driven by place cell inputs and self-motion information have the same spacing and direction, which means that the grid cell module can respond the same to these two types of information. This model can provide a reference for the construction of an unmanned agent brain-inspired navigation system.

Toward a Brain-Inspired System: Deep Recurrent Reinforcement Learning for a Simulated Self-Driving Agent.

An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematical programming principle. From the perspective of brain inspiration, reinforcement learning has gained additional interest in solving decision-making tasks as increasing neuroscientific research demonstrates that significant links exist between reinforcement learning and specific neural substrates. Because of the tremendous research that focuses on human brains and reinforcement learning, scientists have investigated how robots can autonomously tackle complex tasks in the form of making a self-driving agent control in a human-like way. In this study, we propose an end-to-end architecture using novel deep-Q-network architecture in conjunction with a recurrence to resolve the problem in the field of simulated self-driving. The main contribution of this study is that we trained the driving agent using a brain-inspired trial-and-error technique, which was in line with the real world situation. Besides, there are three innovations in the proposed learning network: raw screen outputs are the only information which the driving agent can rely on, a weighted layer that enhances the differences of the lengthy episode, and a modified replay mechanism that overcomes the problem of sparsity and accelerates learning. The proposed network was trained and tested under a third-party OpenAI Gym environment. After training for several episodes, the resulting driving agent performed advanced behaviors in the given scene. We hope that in the future, the proposed brain-inspired learning system would inspire practicable self-driving control solutions.

A DIKW Architecture for Cognitive Engineering

Though the word “cognitive” has a wide range of meanings we define cognitive engineering as learning from brain to bolster engineering solutions. However, giving an achievable framework to the process towards this has been a difficult task. In this work we take the classic data-information-knowledge-wisdom (DIKW) framework to set some achievable goals and sub-goals towards cognitive engineering. A layered framework like DIKW aligns nicely with the layered structure of pre-frontal cortex. And breaking the task into sub-tasks based on the layers also makes it easier to start developmental endeavours towards achieving the final goal of a brain-inspired system.

A brain-inspired SLAM system based on ORB features

This paper describes a brain-inspired simultaneous localization and mapping (SLAM) system using oriented features from accelerated segment test and rotated binary robust independent elementary (ORB) features of RGB (red, green, blue) sensor for a mobile robot. The core SLAM system, dubbed RatSLAM, can construct a cognitive map using information of raw odometry and visual scenes in the path traveled. Different from existing RatSLAM system which only uses a simple vector to represent features of visual image, in this paper, we employ an efficient and very fast descriptor method, called ORB, to extract features from RGB images. Experiments show that these features are suitable to recognize the sequences of familiar visual scenes. Thus, while loop closure errors are detected, the descriptive features will help to modify the pose estimation by driving loop closure and localization in a map correction algorithm. Efficiency and robustness of our method are also demonstrated by comparing with different visual processing algorithms.

The design of a brain sensory organ monitoring thinking activity inside the knowledge system: the brain system

In this article, by adopting brain functions, a brain-inspired system which has a hierarchical structure is designed. In particular, a brain sensory organ is defined as the 6th sense monitoring the brain’s activities of sensing input data, monitoring thinking activities, and maintaining the memory. This brain-inspired system with a brain sensory organ has functions of data acquisition, memory storing and maintenance, and memory recall processes. Emotion and the concept of emotional switching are specially designed and specified. In addition, a thought chain reaction extraction process by emotional switching, and a dynamic thinking associative map (DTAM) in the brain-inspired system were proposed and tested by sample data in the virtual memory.

Memory retention process by balancing the neutral energy point in a brain-inspired system

This article proposes a memory retention strategy in a knowledge network structure in order to make a more efficient intelligent system. The structure and management strategy of the memory have a great influence on the efficiency of the system. In this approach, the concept of neutral energy is introduced, which is used to represent the state of the knowledge node. The energy value of the node was designed to manage the memory retention and recall process in a brain-inspired system. This strategy was applied to a virtual memory and tested with sample data.