Current deep learning architectures are growing larger in order to learn from
complex datasets. These architectures require giant matrix multiplication
operations to train millions of parameters. Conversely, there is another
growing trend to bring deep learning to low-power, embedded devices. The matrix
operations, associated with both training and testing of deep networks, are
very expensive from a computational and energy standpoint. We present a novel
hashing based technique to drastically reduce the amount of computation needed
to train and test deep networks. Our approach combines recent ideas from
adaptive dropouts and randomized hashing for maximum inner product search to
select the nodes with the highest activation efficiently. Our new algorithm for
deep learning reduces the overall computational cost of forward and
back-propagation by operating on significantly fewer (sparse) nodes. As a
consequence, our algorithm uses only 5% of the total multiplications, while
keeping on average within 1% of the accuracy of the original model. A unique
property of the proposed hashing based back-propagation is that the updates are
always sparse. Due to the sparse gradient updates, our algorithm is ideally
suited for asynchronous and parallel training leading to near linear speedup
with increasing number of cores. We demonstrate the scalability and
sustainability (energy efficiency) of our proposed algorithm via rigorous
experimental evaluations on several real datasets.

提出了一种基于哈希的新技术，通过只处理少量的节点来显著降低训练和测试深度神经网络的计算成本，该算法只使用了原始模型总乘法数的 5％，同时保持平均精度在 1％以内，其更新始终是稀疏的，使得算法非常适合异步和并行训练，端到端实验展示了该算法的可扩展性和可持续性。