Academic Articles & Research Papers

Cybersecurity for distributed energy resources and smart inverters

The increased penetration of distributed energy resources (DER) will significantly increase the number of devices that are owned and controlled by consumers and third‐parties. These devices have a significant dependency on digital communica...

Cybersecurity: Risk management framework and investment cost analysis

Cybersecurity

The Internet has given rise to new opportunities for the public sector to improve efficiency and better serve constituents. But with an increasing reliance on the Internet, digital tools are also exposing the public sector to new risks. Thi...

A systemic framework for addressing cybersecurity in construction

Today, the built environment is designed, built, and managed using digital technology, making it increasingly exposed to cyber security risks. Cybersecurity is a general topic, and the construction sector has been borrowing general solution...

NIST Cybersecurity Framework and MITRE Cybersecurity Criteria

Digital Transformation and Cybersecurity Challenges for Businesses Resilience: Issues and Recommendations

This systematic literature review explores the digital transformation (DT) and cybersecurity implications for achieving business resilience. DT involves transitioning organizational processes to IT solutions, which can result in significant...

Neural Network Methods for Natural Language Processing

Deep learning has attracted dramatic attention in recent years, both in academia and industry. The popular term deep learning generally refers to neural network methods. Indeed, many core ideas and methods were born years ago in the era of ...

A survey of graphs in natural language processing

Abstract Graphs are a powerful representation formalism that can be applied to a variety of aspects related to language processing. We provide an overview of how Natural Language Processing problems have been projected into the graph framew...

Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During t...

Pattern Recognition with Neural Networks in C++

From the Publisher: The addition of artificial neural network computing to traditionalpattern recognition has given rise to a new, different, and more powerful methodology that is presented in this interesting book. This is a practical gui...

Bayesian Nonparametric Federated Learning of Neural Networks

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data...

Neural networks for switching

The author argues that a strong impetus for using neural networks is that they provide a framework for designing massively parallel machines. He notes that the highly interconnected architecture of switching networks suggests similarities t...

A NEURAL NETWORK PRIMER

Neural networks are composed of basic units somewhat analogous to neurons. These units are linked to each other by connections whose strength is modifiable as a result of a learning process or algorithm. Each of these units integrates indep...

Fuzzy logic and neural network handbook

Fuzzy logic principles and algorithms design guidelines for fuzzy logic systems enhanced training algorithms maximum likelihood training temporal difference learning NADINE hybrid learning systems explanation and reasoning within connectivi...

Pattern Recognition and Neural Networks

This 1996 book is a reliable account of the statistical framework for pattern recognition and machine learning. With unparalleled coverage and a wealth of case-studies this book gives valuable insight into both the theory and the enormously...

Neural networks in the capital markets

PART ONE: NEURAL NETWORKS: Introduction Design Considerations Methods for Optimal Network Design Data Modelling Considerations Testing Strategies and Metrics PART TWO: EQUITY APPLICATIONS: Modelling Stock Returns in the Framework of APT: A ...

Hypergraph Neural Networks

In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph structure. Confronting the challenges of learning representation for comp...

cuDNN: Efficient Primitives for Deep Learning

We present a library of efficient implementations of deep learning primitives. Deep learning workloads are computationally intensive, and optimizing their kernels is difficult and time-consuming. As parallel architectures evolve, kernels mu...

Federated Machine Learning

Today’s artificial intelligence still faces two major challenges. One is that, in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to t...

EdgeAIGC: Model caching and resource allocation for edge artificial intelligence generated content

With the rapid development of generative artificial intelligence technology, the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs, which restrict user-s...