TextCNN, the convolutional neural network for text, is a useful deep learning algorithm for sentence classification tasks such as sentiment analysis and question classification[2]. However, neural networks have long been known as black boxes because interpreting them is a challenging task. Researchers have developed several tools to understand a CNN for image classification by deep visualizatio...

We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in lowpower devices such as mobile phones. Inspired by the loop perforation technique from source code optimization, we speed up the bottleneck convolutional layers by skipping their evaluation in some of the spatial positions. We propose and a...

In this paper we evaluate the performance of digital pulse interval modulation (DPIM) with convolutional coding for different values of bit resolution and different sizes of guard bands. We show that convolutional coding is an effective method of improving the error performance of DPIM over optical wireless links. The convolutional coded DPIM with a guard band of 2 slots has the advantage of fi...

The difference between block codes and convolutional codes is the encoding principle. In the block codes, the information bits are followed by the parity bits. In convolutional codes the information bits are spread along the sequence. That means that the convolutional codes map information to code bits not block wise, but sequentially convolve the sequence of information bits according to some ...

The process of determining which disease or condition explains a person’s symptoms and signs can be very complicated and may be inaccurate in some cases. The general belief is that diagnosing diseases relies on doctors’ keen intuition, rich experience and professional equipment. In this work, we employ ideas from recent advances in plantar pressure research and from the powerful capacity of the...

Recently the ‘Million Song Dataset’, containing audio features and metadata for one million songs, was made available. In this paper, we build a convolutional network that is then trained to perform artist recognition, genre recognition and key detection. The network is tailored to summarize the audio features over musically significant timescales. It is infeasible to train the network on all a...

We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks. It involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of adjusted regressors...

Various neural network architectures have been proposed in the literature to model 2D correlations in the input signal, including convolutional layers, frequency LSTMs and 2D LSTMs such as time-frequency LSTMs, grid LSTMs and ReNet LSTMs. It has been argued that frequency LSTMs can model translational variations similar to CNNs, and 2D LSTMs can model even more variations [1], but no proper com...

Convolutional encoding with Viterbi decoding is a powerful method for forward error correction. It has been widely deployed in many wireless communication systems to improve the limited capacity of the communication channels. The Viterbi algorithm, which is the most extensively employed decoding algorithm for convolutional codes. In this paper, we present a field-programmable gate array impleme...

In this paper, we revisit the forward, backward and bidirectional Bahl-Cocke-Jelinek-Raviv (BCJR) soft-input soft-output (SISO) maximum a posteriori probability (MAP) decoding process of rate-1 binary convolutional codes. From this we establish some interesting explicit relationships between encoding and decoding of rate-1 convolutional codes. We observe that the forward and backward BCJR SISO ...