LightRNN: Memory and Computation-Efficient Recurrent Neural Networks PPT

EXTENSIONS OF RECURRENT NEURAL NETWORK LANGUAGE MODEL.pdf

EfficientHashingwithLookupsintwoMemoryAccesses

Product Description Developing NoC based interconnect tailored to a particular application domain, s

Thisbookdescribesnewtheoriesandapplicationsofartificialneuralnetworks,withaspecialfocusonneuralcompu

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

Long-term Recurrent Convolutional Networks for Visual Recognition and DescriptionJeff Donahue? Lisa

Convolutionalneural networks with intra-layer recurrent connections for scene labeling

深度神经网络（DNN）的条件计算通过运行网络的子集来减少总体计算负荷并提高模型准确性。在这项工作中，我们提出了一个运行时可调节的神经网络（TNN），它可以自适应地自我调节其自身的性能目标和计算资源。.

可直接运行得到代码

DeepNeuralNetworksinaMathematicalFramework，AnthonyL.Caterini•DongEuiChang。2018年新书，介绍深度学习的数学框架和背景。