A. P. James

A. P. James

Ph.D. Griffith University

About

277
Publications
81,892
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,102
Citations

Publications

Publications (277)
Article
Medical image fusion is the process of registering and combining multiple images from single or multiple imaging modalities to improve the imaging quality and reduce randomness and redundancy in order to increase the clinical applicability of medical images for diagnosis and assessment of medical problems. Multi-modal medical image fusion algorithm...
Article
In this paper, we review the different memristive threshold logic (MTL) circuits that are inspired from the synaptic action of flow of neurotransmitters in the biological brain. Brain-like generalisation ability and area minimisation of these threshold logic circuits aim towards crossing the Moore’s law boundaries at device, circuits and systems le...
Preprint
Full-text available
The AI chips increasingly focus on implementing neural computing at low power and cost. The intelligent sensing, automation, and edge computing applications have been the market drivers for AI chips. Increasingly, the generalisation, performance, robustness, and scalability of the AI chip solutions are compared with human-like intelligence abilitie...
Article
Memristor crossbar arrays are used in a wide range of in-memory and neuromorphic computing applications. However, memristor devices suffer from non-idealities that result in the variability of conductive states, making programming them to a desired analog conductance value extremely difficult as the device ages. In theory, memristors can be a nonli...
Article
Full-text available
The methanol carbonylation catalyst, cis-[Rh(CO)2I2]–, has been heterogenised within a dispersible microporous polymer support bearing cationic functionality. The microporous polymer has a core-shell structure in which the porous and insoluble core (a cross-linked co-polymer of divinylbenzene and 4-vinylpyridine) is sterically stabilised by long hy...
Article
The first stage of tactile sensing is data acquisition using tactile sensors and the sensed data is transmitted to the central unit for neuromorphic computing. The memristive crossbars were proposed to use as synapses in neuromorphic computing but device intelligence at the sensor level are not investigated in literature. We propose the concept of...
Preprint
Full-text available
The first stage of tactile sensing is data acquisition using tactile sensors and the sensed data is transmitted to the central unit for neuromorphic computing. The memristive crossbars were proposed to use as synapses in neuromorphic computing but device intelligence at the sensor level are not investigated in literature. We propose the concept of...
Article
Full-text available
The extreme parallelism property warrant convergence of neural networks with that of quantum computing. As the size of the network grows, the classical implementation of neural networks becomes computationally expensive and not feasible. In this paper, we propose a hybrid image classifier model using spiking neural networks (SNN) and quantum circui...
Article
Full-text available
The human brain can be considered as a complex dynamic and recurrent neural network. There are several models for neural networks of the human brain, that cover sensory to cortical information processing. Large majority models include feedback mechanisms that are hard to formalise to realistic applications. Recurrent neural networks and Long short-...
Preprint
div>The methanol carbonylation catalyst, cis -[Rh(CO)<sub>2</sub>I<sub>2</sub>]<sup>–</sup>, has been heterogenised within a dispersible microporous polymer support bearing cationic functionality. The microporous polymer has a core-shell structure in which the porous and insoluble core (a co-polymer of divinylbenzene and 4-vinylpyridine) is suspend...
Article
The AI chips increasingly focus on implementing neural computing at low power and cost. The intelligent sensing, automation, and edge computing applications have been the market drivers for AI chips. Increasingly, the generalisation, performance, robustness, and scalability of the AI chip solutions are compared with human-like intelligence abilitie...
Chapter
This chapter proposes a new hardware-based implementation of real-time face-recognition application that is inspired by the cortical neuron firing in the human brain. The face-recognition method presented here can detect and store the most relevant data at the sensor. Then, in contrast to the software approaches, it uses the proposed memristive thr...
Chapter
Hierarchical Temporal Memory (HTM) is a biologically plausible model of the neocortex that mimics its structure and functionality. The concepts of HTM and sparse distributed patterns produced by the HTM Spatial Pooler can be useful for various applications. This chapter covers the integration of an analog backpropagation learning circuit into memri...
Chapter
The memristor crossbar configuration can emulate dot-product computations in the analog domain and provides a simplistic way to implement a layer of an analog artificial neural network. Multiple crossbars collectively in a modular architecture can implement large neural networks. However, scaling of analog neural networks to numerous layers and a l...
Chapter
The design and on-chip implementation of learning algorithms for neuromorphic spike domain memristive architectures is a challenging problem. In this chapter, we provide a short overview of the challenges, open problems, architectures and state of the art implementations of spike-based CMOS-memristive neural networks and systems. The importance of...
Article
Reliable programming crossbar memristors to the required resistive states is the challenge that hinders VLSI deployment of the memristive neural network circuits, as current memristive devices face the variability issues of resistive switching. There is also a need for on-chip control circuitry that detects malfunctioning memristive nodes in the cr...
Article
Randomly switching neurons ON/OFF while training and inference process is an interesting characteristic of biological neural networks, that potentially results in inherent adaptability and creativity expressed by human mind. Dropouts inspire from this random switching behaviour and in the artificial neural network they are used as a regularization...
Article
The neuron behavioral models are inspired by the principle of the firing of neurons, and weighted accumulation of charge for a given set of input stimuli. Biological neurons show dynamic behavior through its feedback and feedforward time-dependent responses. The principle of the firing of neurons inspires threshold logic design by applying threshol...
Article
Full-text available
AI Chip Design Automation In article number 2000075, Alex P. James and co‐workers present a genetic search method for automating the brain‐inspired design of analogue neuro‐memristive chips. Using a hardware‐software codesign framework, the genetic search accounts for non‐idealities of memristive hardware in figuring out the optimal neural network...
Article
Full-text available
Optimization of analogue neural circuit designs is one of the most challenging, complicated, time‐consuming, and expensive tasks. Design automation of analogue neuromemristive chips is made difficult by the need to design chips at low cost, ease of scaling, high‐energy efficiency, and small on‐chip area. The rapid progress in edge AI computing appl...
Preprint
Generative Adversarial Network (GAN) is a well known computationally complex algorithm requiring signficiant computational resources in software implementations including large amount of data to be trained. This makes its implementation in edge devices with conventional microprocessor hardware a slow and difficult task. In this paper, we propose to...
Article
Full-text available
Generative Adversarial Network (GAN) requires extensive computing resources making its implementation in edge devices with conventional microprocessor hardware a slow and difficult, if not impossible task. In this paper, we propose to accelerate these intensive neural computations using memristive neural networks in analog domain. The implementatio...
Article
Full-text available
In this work, we analytically study the peaking phenomenon in the context of linear discriminant analysis in the multivariate Gaussian model under the assumption of a common known covariance matrix. The focus is finite sample setting where the sample size and observation dimension are comparable. Therefore, in order to study the phenomenon in such...
Chapter
This chapter covers the implementation of deep learning neural networks and memristive systems. In particular, deep memristive convolutional neural network (CNN) implementation is illustrated. In addition, the main issues and challenges of deep neural network implementation are discussed.
Chapter
This chapter provides a brief overview of learning algorithms and their implementations on hardware. We focus on memristor based systems for leaning, as this is one of the most promising solutions to implement deep neural network on hardware, due to the small on-chip area and low power consumption.
Chapter
Deep Learning is a promising field of Artificial Intelligence algorithms that have proven to be capable of solving a wide range of tasks including classification, object detection, regression, face recognition, augmented and virtual reality, self-driving cars and many more. This chapter introduces the reader to Deep Learning, its basic principles,...
Chapter
Fuzzy logic inspires from the non-deterministic behaviour of human brain computations. The fusion of neural networks and fuzzy logic such as neuro-fuzzy architectures is natural, as both represent elementary inspiration from brain computations involving learning, adaptation and ability to tolerate noise. This chapter focuses on neuro-fuzzy and alik...
Chapter
This chapter covers the memristive HTM implementations on mixed-signal and analog hardware. Most of the implemented memristive systems are based on modified HTM algorithm. The HTM is often used as a feature encoding and feature extraction tool, and these features are then used with conventional nearest neighbor method for classification.
Chapter
The practical realization of neuro-memristive systems requires highly accurate simulation models, robust devices and validations on device characteristics. This chapter covers the basics of memristor characteristics, models and a succinct review of practically realized memristive devices. Memristors represent a class of two terminal resistive switc...
Chapter
Long Short-term Memory was designed to avoid vanishing and exploding gradient problems in recurrent neural networks. Over the last twenty years, various modifications of an original LSTM cell were proposed. This chapter gives an overview of basic LSTM cell structures and demonstrates forward and backward propagation within the most widely used conf...
Chapter
The outdoor electrical insulators are widely used in power transmission and distribution networks. They provide electrical isolation and mechanical support to conductors. Overhead insulators need to be inspected and monitored regularly to prevent faults and provide permanent electricity for consumers. The condition monitoring system for insulators...
Chapter
Threshold logic gates (TLGs) are known for high-speed and low power consumption, which is essential for applications such as real-time processing and recognition of natural signals, as well as on-chip memory architecture and neural network implementation. Integration of memristors into the design allows extending the capabilities of threshold logic...
Chapter
Analog memory is of great importance in neuromorphic engineering as it enables scalable neural network design and energy efficient implementation of computationally expensive operations. With the advent of memristors, the realization of the analog memory became possible due to the intrinsic properties of memristors such as nanoscale size, non-volat...
Chapter
This chapter presents the general background information about the Hierarchical Temporal Memory (HTM). HTM is a recently proposed cognitive learning algorithm that is intended to emulate the overall structural and functionality of the human neocortex responsible for the high-order functions such as cognition, learning and making predictions. The ma...
Chapter
Mainstream standard LSTM architecture that is currently used in Tensorflow library does not use the original architecture. In fact, there are many different architectures of LSTM. One of the more widely used architectures of LSTM is Coupled Input and Forget Gate (CIFG). It is known more as Gated Recurrent Units (GRU). This chapter will introduce th...
Chapter
TensorFlow is an open-source software Python-based library developed by Google. It has high popularity in machine learning and deep learning area due to its simplicity, flexibility, and compatibility. In this chapter, we introduce the basic syntax of the TensorFlow and its main operations required to construct an artificial neural network. We brief...
Chapter
Deep Neural Network (DNN) has demonstrated a great potential in speech recognition systems. This chapter presents two cases with successful implementations of speech recognition based on DNN models. The first example includes a DNN model developed by Apple for its personal assistant Siri. To detect and recognize a “Hey Siri” phrase program runs a d...
Chapter
This chapter provides with an overview of the motivation and direction for neuro-memristive computing hardware. The emergence of deep learning technologies has been largely attributed to the convergence in the growth on computational capabilities, and that of the large availability of the data resulting from Internet of things applications. The nee...
Article
Hierarchical, modular and sparse information processing are signature characteristics of biological neural networks. These aspects have been the backbone of several artificial neural network designs of the brain-like networks, including Hierarchical Temporal Memory (HTM). The main contribution of this work is showing that Convolutional Neural Netwo...
Preprint
Full-text available
The quantization of weights to binary states in Deep Neural Networks (DNNs) can replace resource-hungry multiply accumulate operations with simple accumulations. Such Binarized Neural Networks (BNNs) exhibit greatly reduced resource and power requirements. In addition, memristors have been shown as promising synaptic weight elements in DNNs. In thi...
Article
The high voltage insulator requires continuous monitoring and inspection to prevent failures and emergencies. Manual inspections are costly as it requires covering a large geographical area where insulators are often subjected to harsh weather conditions. Automatic detection of insulators from aerial images is the first step towards performing real...
Preprint
div> Functionalised hypercrosslinked polymers (HCPs) with surface areas between 213 – 1124 m<sup>2</sup>/g based on a range of monomers containing different chemical moieties are evaluated for CO<sub>2</sub> capture using a pressure swing adsorption (PSA) methodology under humid conditions and elevated temperatures. The networks demonstrated rapid...
Article
Full-text available
High voltage insulator detection and monitoring via drone-based aerial images is a cost-effective alternative in extreme winter conditions and complex terrains. The authors examine different surface conditions of the outdoor electrical insulator that generally occur under winter condition using image processing techniques and state-of-the-art class...
Article
An integrated co-processor chip based on a memristor crossbar array and complementary metal–oxide–semiconductor (CMOS) control circuitry can be used to implement neuromorphic and machine learning algorithms.
Article
Microporous materials are predominantly formed as insoluble powders which means that they can be difficult to process. Here we report a new class of solvent-dispersible porous polymers synthesised by reversible addition-fragmentation chain transfer mediated polymerisation-induced self-assembly (RAFT-mediated PISA), formed from a PEG macro-CTA polym...
Article
Full-text available
Smaller, smarter and faster edge devices in the Internet of things era demands secure data analysis and transmission under resource constraints of hardware architecture. Lightweight cryptography on edge hardware is an emerging topic that is essential to ensure data security in near-sensor computing systems such as mobiles, drones, smart cameras and...
Preprint
Smaller, smarter and faster edge devices in the Internet of things era demands secure data analysis and transmission under resource constraints of hardware architecture. Lightweight cryptography on edge hardware is an emerging topic that is essential to ensure data security in near-sensor computing systems such as mobiles, drones, smart cameras, an...
Conference Paper
Full-text available
A generalized bell-shaped function is an essential building block for a neuro-fuzzy systems and radial basis function neural networks. With the advent of edge computing, analog neuro-chips can potentially speed-up the near sensor computing. In this paper, we present a generalized bell function generator circuit for machine learning architectures....
Conference Paper
Full-text available
The impact of device-to-device, cycle-to-cycle, and parasitic variations in memristor devices on the performance of neural network architectures is not a fully understood topic. In this paper, we present an explicit analysis of memristor variabilities and non-idealities of memristive crossbar based learning architectures. The measurements of real d...
Conference Paper
Full-text available
The scalability and non-ideality issues of the memristor circuits poses several challenges to the implementation of analog memristive probabilistic neural networks in hardware. To meet the emerging challenges of faster edge AI computing devices, the integration of neural networks within or near to the sensor can improve the data processing times, r...
Article
Full-text available
The recurrent neural networks (RNN) found to be an effective tool for approximating dynamic systems dealing with time and order dependent data such as video, audio and others. Long short-term memory (LSTM) is a recurrent neural network with a state memory and multilayer cell structure. Hardware acceleration of LSTM using memristor circuit is an eme...
Article
Full-text available
Astronomical images obtained from existing cameras are subjected to various types of noise artifacts. Impulse noise is one of them and it is visible as dark and bright spots on the image. Common practice to remove impulse noise is to perform averaging of several frames. This will increase signal-to-noise ratio of the image, however, impulse noise m...
Book
This book introduces readers to the fundamentals of deep neural network architectures, with a special emphasis on memristor circuits and systems. At first, the book offers an overview of neuro-memristive systems, including memristor devices, models, and theory, as well as an introduction to deep learning neural networks such as multi-layer networks...
Preprint
p>Water-dispersible porous polymeric dispersions (PPDs) have been synthesised by reversible addition-fragmentation chain transfer mediated polymerisation-induced self-assembly (RAFT-mediated PISA). The core-shell particles posses a microporous core formed from divinylbenzene and fumaronitrile while the outer polyethylene glycol shell enables the pa...
Conference Paper
This study presents an equivalent model of dynamic wireless charging system of electric vehicles to analyze switch on and switch off processes. The effect of switch on and switch off processes on system currents is thoroughly studied. Firstly, circuit model is proposed and resonant circuit analysis is performed with resonant frequency 85 kHz. In ad...
Article
This paper presents a survey of the currently available hardware designs for implementation of the human cortex inspired algorithm, Hierarchical Temporal Memory (HTM). In this review, we focus on the state-of-the-art advances of memristive HTM implementation and related HTM applications. With the advent of edge computing, HTM can be a potential alg...
Preprint
The memristor can be used as non volatile memory (NVM) and for emulating neuron behavior. It has the ability to switch between low resistance $R_{on}$ and high resistance values $R_{off}$, and exhibit the synaptic dynamic behaviour such as potentiation and depression. This paper presents a study on potentiation and depression of memristors in Quad...
Preprint
The automated wafer inspection and quality control is a complex and time-consuming task, which can speed up using neuromorphic memristive architectures, as a separate inspection device or integrating directly into sensors. This paper presents the performance analysis and comparison of different neuromorphic architectures for patterned wafer quality...
Cover Page
Full-text available
Welcome Message! On behalf of the Organizing Committee, we are honored and delighted to welcome you to the 7th International Conference on Computing, Communications and Informatics (ICACCI'18), Bangalore, India. Bangalore, officially known as Bengaluru is the capital of the Indian state of Karnataka. Bangalore is popularly known as the ‘Silicon Va...
Preprint
Full-text available
Analysis of time-series data allows to identify long-term trends and make predictions that can help to improve our lives. With the rapid development of artificial neural networks, long short-term memory (LSTM) recurrent neural network (RNN) configuration is found to be capable in dealing with time-series forecasting problems where data points are t...
Preprint
This paper proposes the implementation of programmable threshold logic gate (TLG) crossbar array based on modified TLG cells for high speed processing and computation. The proposed TLG array operation does not depend on input signal and time pulses, comparing to the existing architectures. The circuit is implemented using TSMC $180nm$ CMOS technolo...