mlsanityData to 14 Oct 2026

Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backprop

arXiv 2212.04614 ↗First posted 9 Dec 2022cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Bio-inspired learning has been gaining popularity recently given that Backpropagation (BP) is not considered biologically plausible. Many algorithms have been proposed in the literature which are all more biologically plausible than BP. However, apart from overcoming the biological implausibility of BP, a strong motivation for using Bio-inspired algorithms remains lacking. In this study, we undertake a holistic comparison of BP vs. multiple Bio-inspired algorithms to answer the question of whether Bio-learning offers additional benefits over BP. We test Bio-algorithms under different design choices such as access to only partial training data, resource constraints in terms of the number of training epochs, sparsification of the neural network parameters and addition of noise to input samples. Through these experiments, we notably find two key advantages of Bio-algorithms over BP. Firstly, Bio-algorithms perform much better than BP when the entire training dataset is not supplied. Four of the five Bio-algorithms tested outperform BP by upto 5% accuracy when only 20% of the training dataset is available. Secondly, even when the full dataset is available, Bio-algorithms learn much quicker and converge to a stable accuracy in far lesser training epochs than BP. Hebbian learning, specifically, is able to learn in just 5 epochs compared to around 100 epochs required by BP. These insights present practical reasons for utilising Bio-learning beyond just their biological plausibility and also point towards interesting new directions for future work on Bio-learning.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 19 of its 49 references that are in the map. First posted on arXiv 9 Dec 2022.

Builds on

19 of 49 references.

References · 19

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  2. 2016Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagationcited by 259
  3. 2016Direct Feedback Alignment Provides Learning in Deep Neural Networkscited by 240
  4. 2014Difference Target Propagationcited by 148
  5. 2018Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architecturescited by 101
  6. 2020Predictive Coding Approximates Backprop along Arbitrary Computation Graphscited by 90
  7. 2019Deep Learning without Weight Transportcited by 87
  8. 2018Differentiable plasticity: training plastic neural networks with backpropagationcited by 84
  9. 2020A Theoretical Framework for Target Propagationcited by 57
  10. 2020Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architecturescited by 56
  11. 2018Unsupervised Learning by Competing Hidden Unitscited by 44
  12. 2018Biologically Motivated Algorithms for Propagating Local Target Representationscited by 43
7 more
  1. 2018Biologically-plausible learning algorithms can scale to large datasetscited by 37
  2. 2019Direct Feedback Alignment with Sparse Connections for Local Learningcited by 26
  3. 2021Hebbian Semi-Supervised Learning in a Sample Efficiency Settingcited by 19
  4. 2021Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworkscited by 19
  5. 2021Backprop-Free Reinforcement Learning with Active Neural Generative Codingcited by 12
  6. 2017Learning in the Machine: the Symmetries of the Deep Learning Channelcited by 10
  7. 2020Enabling Continual Learning with Differentiable Hebbian Plasticitycited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 1; 2026: 2.

9 papers.

  1. 2023Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignmentcited by 15
  2. 2023Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Surveycited by 8
  3. 2023Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Surveycited by 7
  4. 2024Biologically-inspired Semi-supervised Semantic Segmentation for Biomedical Imagingcited by 4
  5. 2025Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networkscited by 4
  6. 2024Unsupervised End-to-End Training with a Self-Defined Targetcited by 1
  7. 2024Memory Networks: Towards Fully Biologically Plausible Learningcited by 0
  8. 2026Hebbian Learning with Global Directioncited by 0
  9. 2026Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraintscited by 0