Design of ADNN, an adaptive deep neural network which results in fast and energy- efficient decision making (inference). Joint optimization of all the exit points in ADNN such that the overall loss is minimized. Results: Experiments on MNIST dataset show that 41.9% of samples exit at the ...
In this work, we propose a deep Deep Convolutional Neural Network architecture based on the FaceNet architecture and the MTCNN model to perform face recognition on a set of thermal data. Tests conducted on the USTC-NVIE dataset show promising results and the possibility of using deep learning in...
In this paper, we propose two novel Adaptive Neural Network Approaches (ANNAs), which are intended to automatically learn the optimal network depth. In particular, the proposed class-independent and class-dependent ANNAs address two main challenges faced
Fig. 1. (A) A shallow (one hidden layer) and (B) a deep (multiple hidden layers) neural network. Various nonlinear functions have been proposed for approximation, pattern recognition, and classification problems. In MLP, the nodes in successive layers are connected and the connections are weig...
In recent years, deep learning has achieved great success in the field of image processing. In the single image super-resolution (SISR) task, the convoluti
The dynamic balance between the excitatory and inhibitory neurons accelerates the convergence of the neural networks and improves their performance. We use the combination of the two mechanisms to propose a deep SNN with adaptive self-feedback and balanced excitatory–inhibitory neurons (BackEISNN). ...
Deep convolutional neural network (CNN) becomes a widely used tool for object detection. Many previous works have achieved excellent performance on object detection benchmarks. However, these works present generic detectors whose performance will drop rapidly when they are applied to a surveillance scen...
A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are hierarchically clustered using an i-vector based distance metric. DN...
Deep Adaptive AEC: Hybrid of Deep Learning and Adaptive Acoustic Echo Cancellation(论文翻译及Pytorch代码实现) 哎哟 电子信息硕士在校生。2 人赞同了该文章 目录 收起 摘要: 1.介绍: 2.方法描述: 2.1.信号模型与经典AEC算法: 2.2.深度自适应AEC: 2.2.1.DNN模块: 2.2.2.线性AEC模块: 2.2.3.损失...
The deep Q-network (DQN) is a value-based reinforcement learning algorithm that uses deep neural network 𝑄𝜃Qθ to approximate the optimal Q-function (action-value function) 𝑄∗Q* [45]. The neural network receives a state 𝑠s as input and produces an estimate of the Q-value fo...