The recent trend toward increasingly deep convolutional neural networks (CNNs) leads to a higher demand of computational power and memory storage. Consequently, the deployment of CNNs in hardware has become more challenging. In this paper, we propose an Intra-Kernel Regular (IKR) pruning scheme to reduce the size and computational complexity of the CNNs by removing redundant weights at a fine-g...

Convolutional neural networks (CNNs) have recently emerged as promising models of human vision based on their ability to predict hemodynamic brain responses to visual stimuli measured with functional magnetic resonance imaging (fMRI). However, the degree to which CNNs can predict temporal dynamics of visual object recognition reflected in neural measures with millisecond precision is less under...

We propose a novel method that uses convolutional neural networks (CNNs) for feature extraction. Not just limited to conventional spatial domain representation, we use multilevel 2D discrete Haar wavelet transform, where image representations are scaled to a variety of different sizes. These are then used to train different CNNs to select features. To be precise, we use 10 different CNNs that s...

This paper proposes a new attention mechanism for neural machine translation (NMT) based on convolutional neural networks (CNNs), which is inspired by the CKY algorithm. The proposed attention represents every possible combination of source words (e.g., phrases and structures) through CNNs, which imitates the CKY table in the algorithm. NMT, incorporating the proposed attention, decodes a targe...

In the last two years, convolutional neural networks (CNNs) have achieved an impressive suite of results on standard recognition datasets and tasks. CNN-based features seem poised to quickly replace engineered representations, such as SIFT and HOG. However, compared to SIFT and HOG, we understand much less about the nature of the features learned by large CNNs. In this paper, we experimentally ...

Convolutional neural networks (CNNs) have become popular especially in computer vision in the last few years because they achieved outstanding performance on different tasks, such as image classifications. We propose a ninelayer CNN for leaf identification using the famous Flavia and Foliage datasets. Usually the supervised learning of deep CNNs requires huge datasets for training. However, the...

Beginning with the seminal work of [1], the last half-decade of artificial intelligence and computer vision has been dominated by the stunning success of convolutional neural networks (CNNs). In visual recognition, a robust classifier must be able to recognize objects under deformation. One solution that has been proposed for improving invariance under rotation is complex-valued CNNs [2, 3]. Wh...

This paper presents an effective TSP (Traveling Salesman Problem) solver for large-scale problems using neural networks. Firstly, in the proposed method, an intractable large-scale TSP is divided into some tractable small-scale problems (clusters) using a clustering technique. Secondly, a visiting order of clusters is determined using chaotic neural networks (CNNs). Thirdly, the small-scale pro...

In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. Our system leverages a large amount of unlabeled data to pre-train word embeddings. We then use a subset of the unlabeled data to fine tune the embeddings using distant supervision. The final CNNs and LSTMs are...

We present an approach to recognition of Croatian traffic signs based on convolutional neural networks (CNNs). A library for quick prototyping of CNNs, with an educational scope, is first developed. An architecture similar to LeNet-5 is then created and tested on the MNIST dataset of handwritten digits where comparable results were obtained. We analyze the FERMASTIF TS2010 dataset and propose a...