# Local Critic Training of Deep Neural Networks

arXiv: https://arxiv.org/abs/1805.01128 · HTML: https://mlsanity.com/paper/1805.01128/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2018.

## Built on by (most cited first, 3 of 3)

- [Local Critic Training for Model-Parallel Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.01963/) (2021)
- [Students are the Best Teacher: Exit-Ensemble Distillation with Multi-Exits](https://mlsanity.com/paper/2104.00299/) (2021)
- [Cortico-cerebellar networks as decoupling neural interfaces](https://mlsanity.com/paper/2110.11501/) (2021)

## Abstract (arXiv)

This paper proposes a novel approach to train deep neural networks by unlocking the layer-wise dependency of backpropagation training. The approach employs additional modules called local critic networks besides the main network model to be trained, which are used to obtain error gradients without complete feedforward and backward propagation processes. We propose a cascaded learning strategy for these local networks. In addition, the approach is also useful from multi-model perspectives, including structural optimization of neural networks, computationally efficient progressive inference, and ensemble classification for performance improvement. Experimental results show the effectiveness of the proposed approach and suggest guidelines for determining appropriate algorithm parameters.