Training binary neural networks without floating point precision
This work addresses efficiency issues in training low-latency, low-energy binary neural networks, representing an incremental improvement.
The authors tackled the problem of inefficient training for binary neural networks by proposing topology changes and strategy training, achieving near state-of-the-art performance with reduced training time and memory usage.
The main goal of this work is to improve the efficiency of training binary neural networks, which are low latency and low energy networks. The main contribution of this work is the proposal of two solutions comprised of topology changes and strategy training that allow the network to achieve near the state-of-the-art performance and efficient training. The time required for training and the memory required in the process are two factors that contribute to efficient training.