Related papers: Computationally efficient neural network classifie…
Neuromorphic engineering makes use of mixed-signal analog and digital circuits to directly emulate the computational principles of biological brains. Such electronic systems offer a high degree of adaptability, robustness, and energy…
Deep neural networks represent the gold standard for image classification. However, they usually need large amounts of data to reach superior performance. In this work, we focus on image classification problems with a few labeled examples…
Epilepsy, affecting approximately 50 million people globally, is characterized by abnormal brain activity and remains challenging to treat. The diagnosis of epilepsy relies heavily on electroencephalogram (EEG) data, where specialists…
Spiking neural networks, also often referred to as the third generation of neural networks, carry the potential for a massive reduction in memory and energy consumption over traditional, second-generation neural networks. Inspired by the…
Deep neural networks have achieved impressive supervised classification performance in many tasks including image recognition, speech recognition, and sequence to sequence learning. However, this success has not been translated to…
We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different…
With the widespread success of deep learning technologies, many trained deep neural network (DNN) models are now publicly available. However, directly reusing the public DNN models for new tasks often fails due to mismatching functionality…
Deep neural networks have been demonstrated impressive results in various cognitive tasks such as object detection and image classification. In order to execute large networks, Von Neumann computers store the large number of weight…
This work presents a novel methodology for analysis and control of nonlinear fluid systems using neural networks. The approach is demonstrated on four different study cases being the Lorenz system, a modified version of the…
Deep learning is one of the most successful and far-reaching strategies used in machine learning today. However, the scale and utility of neural networks is still greatly limited by the current hardware used to train them. These concerns…
Neural networks can be used as approximations of several complex control schemes such as model predictive control. We show in this paper which properties deep neural networks with rectifier linear units as activation functions need to…
Developing a Brain-Computer Interface~(BCI) for seizure prediction can help epileptic patients have a better quality of life. However, there are many difficulties and challenges in developing such a system as a real-life support for…
In this paper, we investigate the effectiveness of deep learning techniques for lung nodule classification in computed tomography scans. Using less than 10,000 training examples, our deep networks perform two times better than a standard…
Identifying epileptic seizures through analysis of the electroencephalography (EEG) signal becomes a standard method for the diagnosis of epilepsy. Manual seizure identification on EEG by trained neurologists is time-consuming,…
Neural networks are known to be effective function approximators. Recently, deep neural networks have proven to be very effective in pattern recognition, classification tasks and human-level control to model highly nonlinear realworld…
Identifying sleep stages and patterns is an essential part of diagnosing and treating sleep disorders. With the advancement of smart technologies, sensor data related to sleeping patterns can be captured easily. In this paper, we propose a…
An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models to be highly unclusterable and thus train models to be more…
The ability to process time-series at low energy cost is critical for many applications. Recurrent neural network, which can perform such tasks, are computationally expensive when implementing in software on conventional computers. Here we…
Capsule networks are recently proposed as an alternative to modern neural network architectures. Neurons are replaced with capsule units that represent specific features or entities with normalized vectors or matrices. The activation of…
Audio classification is considered as a challenging problem in pattern recognition. Recently, many algorithms have been proposed using deep neural networks. In this paper, we introduce a new attention-based neural network architecture…