# Online Spatio-Temporal Learning with Target Projection

arXiv: https://arxiv.org/abs/2304.05124 · HTML: https://mlsanity.com/paper/2304.05124/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 13 of 13)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [Direct Feedback Alignment Provides Learning in Deep Neural Networks](https://mlsanity.com/paper/1609.01596/) (2016)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks](https://mlsanity.com/paper/1910.07407/) (2019)
- [Towards Biologically Plausible Deep Learning](https://mlsanity.com/paper/1502.04156/) (2015)
- [ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescales](https://mlsanity.com/paper/2208.09759/) (2022)
- [Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations](https://mlsanity.com/paper/1810.07411/) (2018)
- [Online Spatio-Temporal Learning in Deep Neural Networks](https://mlsanity.com/paper/2007.12723/) (2020)
- [ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware](https://mlsanity.com/paper/2301.08281/) (2023)

## Built on by (most cited first, 9 of 9)

- [S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks](https://mlsanity.com/paper/2306.15220/) (2023)
- [TESS: A Scalable Temporally and Spatially Local Learning Rule for Spiking Neural Networks](https://mlsanity.com/paper/2502.01837/) (2025)
- [EchoSpike Predictive Plasticity: An Online Local Learning Rule for Spiking Neural Networks](https://mlsanity.com/paper/2405.13976/) (2024)
- [Hardware-accelerated graph neural networks: an alternative approach for neuromorphic event-based audio classification and keyword spotting on SoC FPGA](https://mlsanity.com/paper/2602.16442/) (2026)
- [Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA](https://mlsanity.com/paper/2503.06629/) (2025)
- [Traces Propagation: Memory-Efficient and Scalable Forward-Only Learning in Spiking Neural Networks](https://mlsanity.com/paper/2509.13053/) (2025)
- [Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing](https://mlsanity.com/paper/2405.05141/) (2024)
- [Bruno: Backpropagation Running Undersampled for Novel device Optimization](https://mlsanity.com/paper/2505.17791/) (2025)
- [NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework](https://mlsanity.com/paper/2605.15058/) (2026)

## Abstract (arXiv)

Recurrent neural networks trained with the backpropagation through time (BPTT) algorithm have led to astounding successes in various temporal tasks. However, BPTT introduces severe limitations, such as the requirement to propagate information backwards through time, the weight symmetry requirement, as well as update-locking in space and time. These problems become roadblocks for AI systems where online training capabilities are vital. Recently, researchers have developed biologically-inspired training algorithms, addressing a subset of those problems. In this work, we propose a novel learning algorithm called online spatio-temporal learning with target projection (OSTTP) that resolves all aforementioned issues of BPTT. In particular, OSTTP equips a network with the capability to simultaneously process and learn from new incoming data, alleviating the weight symmetry and update-locking problems. We evaluate OSTTP on two temporal tasks, showcasing competitive performance compared to BPTT. Moreover, we present a proof-of-concept implementation of OSTTP on a memristive neuromorphic hardware system, demonstrating its versatility and applicability to resource-constrained AI devices.