Papers
Topics
Authors
Recent
Search
2000 character limit reached

Task adaption by biologically inspired stochastic comodulation

Published 25 Nov 2023 in cs.LG and cs.CV | (2311.15053v1)

Abstract: Brain representations must strike a balance between generalizability and adaptability. Neural codes capture general statistical regularities in the world, while dynamically adjusting to reflect current goals. One aspect of this adaptation is stochastically co-modulating neurons' gains based on their task relevance. These fluctuations then propagate downstream to guide decision-making. Here, we test the computational viability of such a scheme in the context of multi-task learning. We show that fine-tuning convolutional networks by stochastic gain modulation improves on deterministic gain modulation, achieving state-of-the-art results on the CelebA dataset. To better understand the mechanisms supporting this improvement, we explore how fine-tuning performance is affected by architecture using Cifar-100. Overall, our results suggest that stochastic comodulation can enhance learning efficiency and performance in multi-task learning, without additional learnable parameters. This offers a promising new direction for developing more flexible and robust intelligent systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. How to explain individual classification decisions. The Journal of Machine Learning Research, 11:1803–1831, 2010.
  2. Feedback determines the structure of correlated variability in primary visual cortex. Nature Neuroscience, 21:598–606, 2018. ISSN 1097-6256. doi: 10.1038/s41593-018-0089-1.
  3. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  4. Rich Caruana. Multitask learning. Machine learning, 28:41–75, 1997.
  5. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning, pp.  794–803. PMLR, 2018.
  6. Michael Crawshaw. Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796, 2020.
  7. Language modeling with gated convolutional networks. In International conference on machine learning, pp.  933–941. PMLR, 2017.
  8. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp.  248–255. Ieee, 2009.
  9. Mitigating task interference in multi-task learning via explicit task routing with non-learnable primitives. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  7756–7765, 2023.
  10. Decaf: A deep convolutional activation feature for generic visual recognition. In International conference on machine learning, pp.  647–655. PMLR, 2014.
  11. Mechanisms underlying gain modulation in the cortex. Nature Reviews Neuroscience, 21(2):80–92, 2020.
  12. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning, pp.  1126–1135. PMLR, 2017.
  13. Partitioning neuronal variability. Nature Neuroscience, 17(6):858–865, 2014. ISSN 1097-6256. doi: 10.1038/nn.3711.
  14. On calibration of modern neural networks. In International conference on machine learning, pp.  1321–1330. PMLR, 2017.
  15. Flexible information routing in neural populations through stochastic comodulation. Advances in Neural Information Processing Systems, 32, 2019.
  16. Targeted comodulation supports flexible and accurate decoding in v1. bioRxiv, 2021.
  17. Fine-tuning hierarchical circuits through learned stochastic co-modulation. In NeurIPS’22 Workshop on All Things Attention: Bridging Different Perspectives on Attention, 2022.
  18. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  770–778, 2016.
  19. Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261, 2019.
  20. Long short-term memory. Neural computation, 9(8):1735–1780, 1997.
  21. Circuit models of low-dimensional shared variability in cortical networks. Neuron, 101:1–12, 2019.
  22. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, pp.  448–456. pmlr, 2015.
  23. Multiplicative interactions and where to find them. 2020.
  24. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  25. Learning multiple layers of features from tiny images. 2009.
  26. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
  27. An analysis of pre-training on object detection. arXiv preprint arXiv:1904.05871, 2019.
  28. How biological attention mechanisms improve task performance in a large-scale visual system model. eLife, pp.  1–29, 2018. doi: 10.1101/233338.
  29. End-to-end multi-task learning with attention. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  1871–1880, 2019.
  30. Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV), December 2015.
  31. Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.  7765–7773, 2018.
  32. Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In Proceedings of the European conference on computer vision (ECCV), pp.  67–82, 2018.
  33. Attentive single-tasking of multiple tasks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  1851–1860, 2019.
  34. Pretraining boosts out-of-domain robustness for pose estimation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp.  1859–1868, 2021.
  35. John HR Maunsell. Neuronal mechanisms of visual attention. Annual review of vision science, 1:373–391, 2015.
  36. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.
  37. Obtaining well calibrated probabilities using bayesian binning. In Proceedings of the AAAI conference on artificial intelligence, volume 29, 2015.
  38. Invariant neural subspaces maintained by feedback modulation. Elife, 11:e76096, 2022.
  39. Maximum roaming multi-task learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  9331–9341, 2021.
  40. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  41. Film: Visual reasoning with a general conditioning layer. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
  42. Attentional enhancement via selection and pooling of early sensory responses in human visual cortex. Neuron, 72(5):832–846, 2011.
  43. Attention stabilizes the shared gain of V4 populations. eLife, pp.  1–24, 2015. doi: 10.7554/eLife.08998.
  44. Priority coding in the visual system. Nature Reviews Neuroscience, 0123456789, 2022. ISSN 1471-003X. doi: 10.1038/s41583-022-00582-9.
  45. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, 31, 2018.
  46. Computational models link cellular mechanisms of neuromodulation to large-scale neural dynamics. Nature Neuroscience, 24(6):765–776, 2021. ISSN 15461726. doi: 10.1038/s41593-021-00824-6.
  47. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034, 2013.
  48. Many task learning with task routing. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  1375–1384, 2019.
  49. Task switching network for multi-task learning. In Proceedings of the IEEE/CVF international conference on computer vision, pp.  8291–8300, 2021.
  50. Rethinking few-shot image classification: a good embedding is all you need? In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIV 16, pp.  266–282. Springer, 2020.
  51. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  52. Conditional image generation with pixelcnn decoders. Advances in neural information processing systems, 29, 2016.
  53. Multi-task learning for dense prediction tasks: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(7):3614–3633, 2021.
  54. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  55. How transferable are features in deep neural networks? Advances in neural information processing systems, 27, 2014.
  56. Continual learning of context-dependent processing in neural networks. Nature Machine Intelligence, 1(8):364–372, 2019.
  57. Side-tuning: a baseline for network adaptation via additive side networks. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, pp.  698–714. Springer, 2020.
  58. Facial landmark detection by deep multi-task learning. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13, pp.  94–108. Springer, 2014.
  59. A modulation module for multi-task learning with applications in image retrieval. In Proceedings of the European Conference on Computer Vision (ECCV), pp.  401–416, 2018.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up