It is well known that one-dimensional cellular neural networks (1-D CNNs) with the template A = [1, 2,−1] can perform connected component detection (CCD). However this has been confirmed only by numerical and laboratory experiments. In this paper, sufficient conditions for 1-D CNNs to perform CCD are obtained through theoretical analysis. Main result shows that a wide class of templates includi...

This paper deals with the obtention of robust parameter configurations for DT-CNNs and for a class of CT-CNNs (here called CT-CNNs with Discrete Configurations, DC-CT-CNN), in the presence of additive and multiplicative implementation errors. Expressions that characterize the tolerance to both multiplicative and additive errors caused by circuit inaccuracies in DT-CNNs and DC-CT-CNNs VLSI imple...

Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudotokens for CNNs. With this method, we establish a new state-of-the-art result...

We study the event detection problem using convolutional neural networks (CNNs) that overcome the two fundamental limitations of the traditional feature-based approaches to this task: complicated feature engineering for rich feature sets and error propagation from the preceding stages which generate these features. The experimental results show that the CNNs outperform the best reported feature...

Introduction: Recent studies have acknowledged the potential of convolutional neural networks (CNNs) in distinguishing healthy and morbid samples by using heart sound analyses. Unfortunately the performance of CNNs is highly dependent on the filtering procedure which is applied to signal in their convolutional layer. The present study aimed to address this problem by a...

Structure pruning is an effective method to compress and accelerate neural networks. While filter channel are preferable other structure methods in terms of realistic acceleration hardware compatibility, with a finer granularity, such as intra-channel pruning, expected be capable yielding more compact computationally efficient Typical utilize static hand-crafted granularity due large search spa...

Wepropose a newmodel of Chaotic Cellular Neural Networks (C-CNNs) by introducing negative self-feedback into the Euler approximation of the continuous CNNs. According to our simulation result for the single neuron model, this new C-CNN model has richer and more flexible dynamics, compared to the conventional CNN with only stable dynamics. The hardware implementation of this new network may be i...

We combine features extracted from pre-trained convolutional neural networks (CNNs) with the fast, linear Exemplar-LDA classifier to get the advantages of both: the high detection performance of CNNs, automatic feature engineering, fast model learning from few training samples and efficient sliding-window detection. The Adaptive Real-Time Object Detection System (ARTOS) has been refactored broa...

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking dat...