# full-FORCE: A Target-Based Method for Training Recurrent Networks

arXiv: https://arxiv.org/abs/1710.03070 · HTML: https://mlsanity.com/paper/1710.03070/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2017.

## Built on by (most cited first, 16 of 16)

- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [Backpropagation through space, time, and the brain](https://mlsanity.com/paper/2403.16933/) (2024)
- [Input correlations impede suppression of chaos and learning in balanced rate networks](https://mlsanity.com/paper/2201.09916/) (2022)
- [Lyapunov-Guided Representation of Recurrent Neural Network Performance](https://mlsanity.com/paper/2204.04876/) (2022)
- [Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules](https://mlsanity.com/paper/2206.00823/) (2022)
- [Learning in Feedback-driven Recurrent Spiking Neural Networks using full-FORCE Training](https://mlsanity.com/paper/2205.13585/) (2022)
- [Augmenting learning in neuro-embodied systems through neurobiological first principles](https://mlsanity.com/paper/2407.04525/) (2024)
- [Path classification by stochastic linear recurrent neural networks](https://mlsanity.com/paper/2108.03090/) (2021)
- [Composite FORCE learning of chaotic echo state networks for time-series prediction](https://mlsanity.com/paper/2207.02420/) (2022)
- [Emergent Computations in Trained Artificial Neural Networks and Real Brains](https://mlsanity.com/paper/2212.04938/) (2022)
- [Separation capacity of linear reservoirs with random connectivity matrix](https://mlsanity.com/paper/2404.17429/) (2024)
- [Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example](https://mlsanity.com/paper/2506.06904/) (2025)
- [Neuronal architecture extracts statistical temporal patterns](https://mlsanity.com/paper/2301.10203/) (2023)
- [Learning fast changing slow in spiking neural networks](https://mlsanity.com/paper/2402.10069/) (2024)
- [Machine Learning Methods for Studying Latent Neural Activity Dynamics](https://mlsanity.com/paper/2606.10530/) (2026)
- [From Digital to Physical Reservoir Computing: Co-Optimizing Soft Robotic Reservoirs via Dynamics Matching](https://mlsanity.com/paper/2608.00484/) (2026)

## Abstract (arXiv)

Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during training to provide suitable "target" dynamics useful for performing the task. Because it exploits the full recurrent connectivity, the method produces networks that perform tasks with fewer neurons and greater noise robustness than traditional least-squares (FORCE) approaches. In addition, we show how introducing additional input signals into the target-generating network, which act as task hints, greatly extends the range of tasks that can be learned and provides control over the complexity and nature of the dynamics of the trained, task-performing network.