Algorithms for Efficient Inference in Convolutional Neural Networks

In recent years, the accuracy of Deep Neural Networks (DNNs) has improved significantly because of three main factors: the availability of massive amounts training data, the introduction of powerful low-cost computational resources, and the development of complex deep learning models. The cloud can provide powerful computational resources to...

An Attention Module for Convolutional Neural Networks

Attention mechanism has been regarded as an advanced technique to capture long-range feature interactions and to boost the representation capability for convolutional neural networks. However, we found two ignored problems in current attentional activations-based models: the approximation problem and the insufficient capacity problem of the...

ReAF: Reducing approximation of channels by reducing feature reuse within convolution

High-level feature maps of Convolutional Neural Networks are computed by reusing their corresponding low-level feature maps, which brings into full play feature reuse to improve the computational efficiency. This form of feature reuse is referred to as feature reuse between convolutional layers. The second type of feature reuse is referred to...

A spatial agent based model for simulating and optimizing networked eco-industrial systems

Industrial symbiosis involves creating integrated cycles of by-products and waste between networks of industrial actors in order to maximize economic value, while at the same time minimizing environmental strain. In such a network, the global environmental strain is no longer equal to the sum of the environmental strain of the individual...

Towards lossless binary convolutional neural networks using piecewise approximation

Binary Convolutional Neural Networks (CNNs) can significantly reduce the number of arithmetic operations and the size of memory storage, which makes the deployment of CNNs on mobile or embedded systems more promising. However, the accuracy degradation of single and multiple binary CNNs is unacceptable for modern architectures and large scale...

NASB: Neural Architecture Search for Binary Convolutional Neural Networks

Binary Convolutional Neural Networks (CNNs) have significantly reduced the number of arithmetic operations and the size of memory storage needed for CNNs, which makes their deployment on mobile and embedded systems more feasible. However, after binarization, the CNN architecture has to be redesigned and refined significantly due to two reasons:...

Secondary Resources in the Bio-Based Economy: A Computer Assisted Survey of Value Pathways in Academic Literature

Research on value pathways for organic wastes has been steadily increasing in recent decades. There have been few considerably broad overview studies of such materials and their valuation potential in the bio-based economy in part because of the vast multitude of materials and processes that can be used to produce energy carriers, chemicals,...

Life cycle assessment and simplified life cycle costing on Industrial Symbiosis

This paper adopts the life cycle thinking as the approach to assess the economic and environmental performances of industrial symbiosis. A detailed guidance of implementing LCA on industrial symbiosis under four research purposes: accounting of symbiosis, existing symbiosis, exploring symbiosis and comparing symbiosis design options is presented...