Unexpected Benefits of Self-Modeling in Neural Systems

• URL: http://arxiv.org/abs/2407.10188v2
• Date: Tue, 23 Jul 2024 21:54:12 GMT
• Title: Unexpected Benefits of Self-Modeling in Neural Systems
• Authors: Vickram N. Premakumar, Michael Vaiana, Florin Pop, Judd Rosenblatt, Diogo Schwerz de Lucena, Kirsten Ziman, Michael S. A. Graziano,
• Abstract summary: We show that when artificial networks learn to predict their internal states as an auxiliary task, they change in a fundamental way. To better perform the self-model task, the network learns to make itself simpler, more regularized, more parameter-efficient. This self-regularization may help explain some of the benefits of self-models reported in recent machine learning literature.
• Score: 0.7179624965454197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-models have been a topic of great interest for decades in studies of human cognition and more recently in machine learning. Yet what benefits do self-models confer? Here we show that when artificial networks learn to predict their internal states as an auxiliary task, they change in a fundamental way. To better perform the self-model task, the network learns to make itself simpler, more regularized, more parameter-efficient, and therefore more amenable to being predictively modeled. To test the hypothesis of self-regularizing through self-modeling, we used a range of network architectures performing three classification tasks across two modalities. In all cases, adding self-modeling caused a significant reduction in network complexity. The reduction was observed in two ways. First, the distribution of weights was narrower when self-modeling was present. Second, a measure of network complexity, the real log canonical threshold (RLCT), was smaller when self-modeling was present. Not only were measures of complexity reduced, but the reduction became more pronounced as greater training weight was placed on the auxiliary task of self-modeling. These results strongly support the hypothesis that self-modeling is more than simply a network learning to predict itself. The learning has a restructuring effect, reducing complexity and increasing parameter efficiency. This self-regularization may help explain some of the benefits of self-models reported in recent machine learning literature, as well as the adaptive value of self-models to biological systems. In particular, these findings may shed light on the possible interaction between the ability to model oneself and the ability to be more easily modeled by others in a social or cooperative context.

Related papers

• RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively [10.812755570974929]
  We use Model Structural Redundancy Score (MSRS) to measure the degree of redundancy in a deep learning model structure. MSRS is effective in both revealing and assessing the redundancy issues in many state-of-the-art models. We design a novel redundancy-aware algorithm to guide the search for the optimal model structure.
  arXiv  Detail & Related papers  (2024-11-15T14:36:07Z)
• Transferable Post-training via Inverse Value Learning [83.75002867411263]
  We propose modeling changes at the logits level during post-training using a separate neural network (i.e., the value network) After training this network on a small base model using demonstrations, this network can be seamlessly integrated with other pre-trained models during inference. We demonstrate that the resulting value network has broad transferability across pre-trained models of different parameter sizes.
  arXiv  Detail & Related papers  (2024-10-28T13:48:43Z)
• A Dynamical Model of Neural Scaling Laws [79.59705237659547]
  We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
  arXiv  Detail & Related papers  (2024-02-02T01:41:38Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Cooperative data-driven modeling [44.99833362998488]
  Data-driven modeling in mechanics is evolving rapidly based on recent machine learning advances. New data and models created by different groups become available, opening possibilities for cooperative modeling. Artificial neural networks suffer from catastrophic forgetting, i.e. they forget how to perform an old task when trained on a new one. This hinders cooperation because adapting an existing model for a new task affects the performance on a previous task trained by someone else.
  arXiv  Detail & Related papers  (2022-11-23T14:27:25Z)
• Slimmable Networks for Contrastive Self-supervised Learning [69.9454691873866]
  Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. We introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers. A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks.
  arXiv  Detail & Related papers  (2022-09-30T15:15:05Z)
• Self-Damaging Contrastive Learning [92.34124578823977]
  Unlabeled data in reality is commonly imbalanced and shows a long-tail distribution. This paper proposes a principled framework called Self-Damaging Contrastive Learning to automatically balance the representation learning without knowing the classes. Our experiments show that SDCLR significantly improves not only overall accuracies but also balancedness.
  arXiv  Detail & Related papers  (2021-06-06T00:04:49Z)
• Distill on the Go: Online knowledge distillation in self-supervised learning [1.1470070927586016]
  Recent works have shown that wider and deeper models benefit more from self-supervised learning than smaller models. We propose Distill-on-the-Go (DoGo), a self-supervised learning paradigm using single-stage online knowledge distillation. Our results show significant performance gain in the presence of noisy and limited labels.
  arXiv  Detail & Related papers  (2021-04-20T09:59:23Z)
• Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems [31.702684333839585]
  We show that improving a machine-learning model can deteriorate the performance of downstream models. We identify different types of entanglement and demonstrate via simple experiments how they can produce self-defeating improvements. We also show that self-defeating improvements emerge in a realistic stereo-based object detection system.
  arXiv  Detail & Related papers  (2021-03-22T12:29:10Z)
• Counterfactual Generative Networks [59.080843365828756]
  We propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision. By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background. We show that the counterfactual images can improve out-of-distribution with a marginal drop in performance on the original classification task.
  arXiv  Detail & Related papers  (2021-01-15T10:23:12Z)
• The Self-Simplifying Machine: Exploiting the Structure of Piecewise Linear Neural Networks to Create Interpretable Models [0.0]
  We introduce novel methodology toward simplification and increased interpretability of Piecewise Linear Neural Networks for classification tasks. Our methods include the use of a trained, deep network to produce a well-performing, single-hidden-layer network without further training. On these methods, we conduct preliminary studies of model performance, as well as a case study on Wells Fargo's Home Lending dataset.
  arXiv  Detail & Related papers  (2020-12-02T16:02:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.