# Emulation Learning for Neuromimetic Systems

arXiv: https://arxiv.org/abs/2305.03196 · HTML: https://mlsanity.com/paper/2305.03196/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 11 of 11)

- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [Transfer Learning in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2009.07888/) (2020)
- [Deep Reinforcement Learning and the Deadly Triad](https://mlsanity.com/paper/1812.02648/) (2018)
- [Convergent and Efficient Deep Q Network Algorithm](https://mlsanity.com/paper/2106.15419/) (2021)
- [Saliency Based Control in Random Feature Networks](https://mlsanity.com/paper/1403.5462/) (2014)
- [Perceptual Control with Large Feature and Actuator Networks](https://mlsanity.com/paper/1903.10259/) (2019)
- [Neuromimetic Control -- A Linear Model Paradigm](https://mlsanity.com/paper/2104.12926/) (2021)
- [Neuromimetic Linear Systems -- Resilience and Learning](https://mlsanity.com/paper/2205.05013/) (2022)
- [Model Predictive Control for Neuromimetic Quantized Systems](https://mlsanity.com/paper/2212.09887/) (2022)

## Built on by (most cited first, 1 of 1)

- [Koopman-based Deep Learning for Nonlinear System Estimation](https://mlsanity.com/paper/2405.00627/) (2024)

## Abstract (arXiv)

Building on our recent research on neural heuristic quantization systems, results on learning quantized motions and resilience to channel dropouts are reported. We propose a general emulation problem consistent with the neuromimetic paradigm. This optimal quantization problem can be solved by model predictive control (MPC), but because the optimization step involves integer programming, the approach suffers from combinatorial complexity when the number of input channels becomes large. Even if we collect data points to train a neural network simultaneously, collection of training data and the training itself are still time-consuming. Therefore, we propose a general Deep Q Network (DQN) algorithm that can not only learn the trajectory but also exhibit the advantages of resilience to channel dropout. Furthermore, to transfer the model to other emulation problems, a mapping-based transfer learning approach can be used directly on the current model to obtain the optimal direction for the new emulation problems.