摘要:
1. The State of Sparsity in Deep Neural Networks(2019 optional) 工作 We perform a comprehensive evaluation of variational dropout , l0 regularization (L 阅读全文
摘要:
1. Theano: A CPU and GPU Math Compiler in Python(2010 optional) 动机 Python is slow, one reason is that Python uses full-fledged Python objects on the h 阅读全文
摘要:
1. Neural Adaptive Video Streaming with Pensieve (require 2017 MIT) 动机 Adaptive bitrate (ABR) algorithms are the primary tool that content providers u 阅读全文
摘要:
1. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima(Optional 2017 Northwestern University) 动机 SGD and its variants理论属性: 阅读全文
摘要:
1. Large Scale Distributed Deep Networks(Optional 2012, Google Jeffrey Dean) 动机: we consider the problem of training a deep network with billions of p 阅读全文
摘要:
1. Interstellar: using halide’s scheduling language to analyze dnn accelerators (formerly: dnn dataflow choice is overrated. 动机 CNN存在大量的数据reuse,这为局部性优 阅读全文