Training binary neural networks without floating point precision
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). First posted on arXiv 19 Oct 2023.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2021Improving Binary Neural Networks through Fully Utilizing Latent Weights
- 2024Training Multi-Layer Binary Neural Networks With Local Binary Error Signals
- 2024CycleBNN: Cyclic Precision Training in Binary Neural Networks
- 2023Optimizing data-flow in Binary Neural Networks
- 2021Enabling Binary Neural Network Training on the Edge
- 2021BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements
- 2022Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks
- 2023Binary domain generalization for sparsifying binary neural networks