mlsanityData to 13 Oct 2026

Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence

arXiv 2106.01288 ↗First posted 2 Jun 2021cs.NE cs.AI cs.ETcited by 21

Not on the map. Why?

Abstract (arXiv)

While Moore's law has driven exponential computing power expectations, its nearing end calls for new avenues for improving the overall system performance. One of these avenues is the exploration of alternative brain-inspired computing architectures that aim at achieving the flexibility and computational efficiency of biological neural processing systems. Within this context, neuromorphic engineering represents a paradigm shift in computing based on the implementation of spiking neural network architectures in which processing and memory are tightly co-located. In this paper, we provide a comprehensive overview of the field, highlighting the different levels of granularity at which this paradigm shift is realized and comparing design approaches that focus on replicating natural intelligence (bottom-up) versus those that aim at solving practical artificial intelligence applications (top-down). First, we present the analog, mixed-signal and digital circuit design styles, identifying the boundary between processing and memory through time multiplexing, in-memory computation, and novel devices. Then, we highlight the key tradeoffs for each of the bottom-up and top-down design approaches, survey their silicon implementations, and carry out detailed comparative analyses to extract design guidelines. Finally, we identify necessary synergies and missing elements required to achieve a competitive advantage for neuromorphic systems over conventional machine-learning accelerators in edge computing applications, and outline the key ingredients for a framework toward neuromorphic intelligence.

Key facts. Cited by 21 papers in the map (data through 13 Oct 2026). Builds on 78 of its 363 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

78 of 363 references.

References · 78

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,601
  4. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,056
  5. 2020Meta-Learning in Neural Networks: A Surveycited by 945
  6. 2014Deep Learning in Neural Networks: An Overviewcited by 767
  7. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 617
  8. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 514
  9. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  10. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 433
  11. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 422
  12. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 313
38 more
  1. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 263
  2. 2016Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagationcited by 255
  3. 2016Direct Feedback Alignment Provides Learning in Deep Neural Networkscited by 240
  4. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 228
  5. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 217
  6. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 205
  7. 2020The Computational Limits of Deep Learningcited by 190
  8. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 180
  9. 2014Difference Target Propagationcited by 146
  10. 2019The Heidelberg spiking datasets for the systematic evaluation of spiking neural networkscited by 137
  11. 2016Decoupled Neural Interfaces using Synthetic Gradientscited by 136
  12. 2019Training Neural Networks with Local Error Signalscited by 135
  13. 2018Dendritic cortical microcircuits approximate the backpropagation algorithmcited by 97
  14. 2020Benchmarking TinyML Systems: Challenges and Directioncited by 91
  15. 2017A Survey of Neuromorphic Computing and Neural Networks in Hardwarecited by 84
  16. 2016Supervised learning based on temporal coding in spiking neural networkscited by 76
  17. 2016Towards deep learning with segregated dendritescited by 71
  18. 2015Towards Biologically Plausible Deep Learningcited by 66
  19. 2018Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rulescited by 64
  20. 2015How Important is Weight Symmetry in Backpropagation?cited by 57
  21. 2020A Theoretical Framework for Target Propagationcited by 57
  22. 2017A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)cited by 52
  23. 2019Fast and energy-efficient neuromorphic deep learning with first-spike timescited by 52
  24. 2021Brain-inspired computing: We need a master plancited by 51
  25. 2019S4NN: temporal backpropagation for spiking neural networks with one spike per neuroncited by 49
  26. 2015Memory and information processing in neuromorphic systemscited by 48
  27. 2017Gradient Descent for Spiking Neural Networkscited by 48
  28. 2021Posterior Meta-Replay for Continual Learningcited by 45
  29. 2017Deep supervised learning using local errorscited by 41
  30. 2016Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardwarecited by 40
  31. 2020Meta-learning in natural and artificial intelligencecited by 39
  32. 2016Neuromorphic Deep Learning Machinescited by 38
  33. 2020Surrogate gradients for analog neuromorphic computingcited by 38
  34. 2018Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardwarecited by 37
  35. 2020Brain-Inspired Learning on Neuromorphic Substratescited by 37
  36. 2017Understanding Synthetic Gradients and Decoupled Neural Interfacescited by 35
  37. 2020Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applicationscited by 34
  38. 2020DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip Trainingcited by 33

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 4; 2024: 4; 2025: 9; 2026: 3.

21 papers.

Sort:

By area:

  1. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 256
  2. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 99
  3. 2023Fully neuromorphic vision and control for autonomous drone flightcited by 30
  4. 2023NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systemscited by 27
  5. 2023To Spike or Not To Spike: A Digital Hardware Perspective on Deep Learning Accelerationcited by 10
  6. 2023Applications of Spiking Neural Networks in Visual Place Recognitioncited by 9
  7. 2024DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardwarecited by 9
  8. 2024Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoderscited by 5
  9. 2025SpikingBrain: Spiking Brain-inspired Large Modelscited by 5
  10. 2025SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) Complexitycited by 4
  11. 2025Causal pieces: analysing and improving spiking neural networks piece by piececited by 2
  12. 2025Edge Intelligence with Spiking Neural Networkscited by 2
9 more
  1. 2025New Spiking Architecture for Multi-Modal Decision-Making in Autonomous Vehiclescited by 2
  2. 2026Accelerated Predictive Coding Networks via Direct Kolen-Pollack Feedback Alignmentcited by 2
  3. 2026SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inferencecited by 2
  4. 2024STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networkscited by 1
  5. 2025Assessing the Performance of Analog Training for Transfer Learningcited by 1
  6. 2025Memristor-Based Neural Network Accelerators for Space Applications: Enhancing Performance with Temporal Averaging and SIRENscited by 1
  7. 2025On the Importance of Neural Membrane Potential Leakage for LIDAR-based Robot Obstacle Avoidance using Spiking Neural Networkscited by 0
  8. 2025Decoding Listeners Identity: Person Identification from EEG Signals Using a Lightweight Spiking Transformercited by 0
  9. 2026The SpiNNaker2 chip: a many-core platform for flexible and scalable brain-inspired computingcited by 0