mlsanityData to 7 Oct 2026

Online Spatio-Temporal Learning with Target Projection

arXiv 2304.05124 ↗First posted 11 Apr 2023cs.NE cs.LGcited by 9

Not on the map. Why?

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 11 Apr 2023.

Builds on

13 of 25 references.

References · 13

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
  3. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  4. 2015Listen, Attend and Spellcited by 542
  5. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  6. 2016Direct Feedback Alignment Provides Learning in Deep Neural Networkscited by 240
  7. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  8. 2019The Heidelberg spiking datasets for the systematic evaluation of spiking neural networkscited by 135
  9. 2015Towards Biologically Plausible Deep Learningcited by 66
  10. 2022ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescalescited by 35
  11. 2018Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representationscited by 32
  12. 2020Online Spatio-Temporal Learning in Deep Neural Networkscited by 32
1 more
  1. 2023ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardwarecited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 4; 2026: 2.

9 papers.

  1. 2023S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networkscited by 7
  2. 2025TESS: A Scalable Temporally and Spatially Local Learning Rule for Spiking Neural Networkscited by 4
  3. 2024EchoSpike Predictive Plasticity: An Online Local Learning Rule for Spiking Neural Networkscited by 2
  4. 2026Hardware-accelerated graph neural networks: an alternative approach for neuromorphic event-based audio classification and keyword spotting on SoC FPGAcited by 2
  5. 2025Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGAcited by 1
  6. 2025Traces Propagation: Memory-Efficient and Scalable Forward-Only Learning in Spiking Neural Networkscited by 1
  7. 2024Learning-to-learn enables rapid learning with phase-change memory-based in-memory computingcited by 0
  8. 2025Bruno: Backpropagation Running Undersampled for Novel device Optimizationcited by 0
  9. 2026NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Frameworkcited by 0