Dual Cognitive Architecture: Incorporating Biases and Multi-Memory Systems for Lifelong Learning (2310.11341v1)
Abstract: Artificial neural networks (ANNs) exhibit a narrow scope of expertise on stationary independent data. However, the data in the real world is continuous and dynamic, and ANNs must adapt to novel scenarios while also retaining the learned knowledge to become lifelong learners. The ability of humans to excel at these tasks can be attributed to multiple factors ranging from cognitive computational structures, cognitive biases, and the multi-memory systems in the brain. We incorporate key concepts from each of these to design a novel framework, Dual Cognitive Architecture (DUCA), which includes multiple sub-systems, implicit and explicit knowledge representation dichotomy, inductive bias, and a multi-memory system. The inductive bias learner within DUCA is instrumental in encoding shape information, effectively countering the tendency of ANNs to learn local textures. Simultaneously, the inclusion of a semantic memory submodule facilitates the gradual consolidation of knowledge, replicating the dynamics observed in fast and slow learning systems, reminiscent of the principles underpinning the complementary learning system in human cognition. DUCA shows improvement across different settings and datasets, and it also exhibits reduced task recency bias, without the need for extra information. To further test the versatility of lifelong learning methods on a challenging distribution shift, we introduce a novel domain-incremental dataset DN4IL. In addition to improving performance on existing benchmarks, DUCA also demonstrates superior performance on this complex dataset.
- Learning fast, learning slow: A general continual learning method based on complementary learning system. In International Conference on Learning Representations, 2022. URL https://openreview.net/forum?id=uxxFrDwrE7Y.
- Consistency is the key to further mitigating catastrophic forgetting in continual learning. In Conference on Lifelong Learning Agents, pp. 1195–1212. PMLR, 2022.
- Dark experience for general continual learning: a strong, simple baseline. Advances in neural information processing systems, 33:15920–15930, 2020.
- New insights on reducing abrupt representation change in online continual learning. In International Conference on Learning Representations, 2021.
- Co2l: Contrastive continual learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9516–9525, 2021.
- Dual-process theories in social psychology. Guilford Press, 1999.
- François Chollet. On the measure of intelligence. arXiv preprint arXiv:1911.01547, 2019.
- On the canny edge detector. Pattern Recognition, 34(3):721–725, 2001.
- Towards robust evaluations of continual learning. arXiv preprint arXiv:1805.09733, 2018.
- Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International Conference on Learning Representations, 2019. URL https://openreview.net/forum?id=Bygh9j09KX.
- Inbiased: Inductive bias distillation to improve generalization and robustness through shape-awareness. In Conference on Lifelong Learning Agents, pp. 1026–1042. PMLR, 2022.
- Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.
- On the link between conscious function and general intelligence in humans and machines. arXiv preprint arXiv:2204.05133, 2022.
- Learning multiple layers of features from tiny images. 2009.
- What learning systems do intelligent agents need? complementary learning systems theory updated. Trends in cognitive sciences, 20(7):512–534, 2016.
- Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
- Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation, volume 24, pp. 109–165. Elsevier, 1989.
- Generalized class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 240–241, 2020.
- Continual lifelong learning with neural networks: A review. Neural Networks, 113:54–71, 2019.
- The book of why: the new science of cause and effect. Basic books, 2018.
- Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF international conference on computer vision, pp. 1406–1415, 2019.
- Learning to learn without forgetting by maximizing transfer and minimizing interference. In International Conference on Learning Representations, 2018.
- Synergy between synaptic consolidation and experience replay for general continual learning. In Conference on Lifelong Learning Agents, pp. 920–936. PMLR, 2022.
- A 3x3 isotropic gradient operator for image processing. a talk at the Stanford Artificial Project in, pp. 271–272, 1968.
- Computational models of consciousness: A taxonomy and some examples., 2007.
- Gido M Van de Ven and Andreas S Tolias. Three scenarios for continual learning. arXiv preprint arXiv:1904.07734, 2019.
- Jeffrey S Vitter. Random sampling with a reservoir. ACM Transactions on Mathematical Software (TOMS), 11(1):37–57, 1985.
- Large scale incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 374–382, 2019.