Brain-like emergent properties in deep networks: impact of network architecture, datasets and training

• URL: http://arxiv.org/abs/2411.16326v1
• Date: Mon, 25 Nov 2024 12:22:36 GMT
• Title: Brain-like emergent properties in deep networks: impact of network architecture, datasets and training
• Authors: Niranjan Rajesh, Georgin Jacob, SP Arun,
• Abstract summary: Despite the rapid pace at which deep networks are improving, they are still outperformed by humans on real-world vision tasks. This paradoxical lack of generalization could be addressed by making deep networks more brain-like. We report several well-known perceptual and neural emergent properties that can be tested on deep networks.
• Score: 3.1893819671093775
• License:
• Abstract: Despite the rapid pace at which deep networks are improving on standardized vision benchmarks, they are still outperformed by humans on real-world vision tasks. This paradoxical lack of generalization could be addressed by making deep networks more brain-like. Although several benchmarks have compared the ability of deep networks to predict brain responses to natural images, they do not capture subtle but important brain-like emergent properties. To resolve this issue, we report several well-known perceptual and neural emergent properties that can be tested on deep networks. To evaluate how various design factors impact brain-like properties, we systematically evaluated over 30 state-of-the-art networks with varying network architectures, training datasets and training regimes. Our main findings are as follows. First, network architecture had the strongest impact on brain-like properties compared to dataset and training regime variations. Second, networks varied widely in their alignment to the brain with no single network outperforming all others. Taken together, our results complement existing benchmarks by revealing brain-like properties that are either emergent or lacking in state-of-the-art deep networks.

Related papers

• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Brain Decodes Deep Nets [9.302098067235507]
  We developed a tool for visualizing and analyzing large pre-trained vision models by mapping them onto the brain. Our innovation arises from a surprising usage of brain encoding: predicting brain fMRI measurements in response to images.
  arXiv  Detail & Related papers  (2023-12-03T04:36:04Z)
• Connecting metrics for shape-texture knowledge in computer vision [1.7785095623975342]
  Deep neural networks remain brittle and susceptible to many changes in the image that do not cause humans to misclassify images. Part of this different behavior may be explained by the type of features humans and deep neural networks use in vision tasks.
  arXiv  Detail & Related papers  (2023-01-25T14:37:42Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation [55.80128181112308]
  We show that dimensionality and quasi-orthogonality of neural networks' feature space may jointly serve as network's performance discriminants. Our findings suggest important relationships between the networks' final performance and properties of their randomly initialised feature spaces.
  arXiv  Detail & Related papers  (2022-03-30T21:47:32Z)
• Creating Powerful and Interpretable Models withRegression Networks [2.2049183478692584]
  We propose a novel architecture, Regression Networks, which combines the power of neural networks with the understandability of regression analysis. We demonstrate that the models exceed the state-of-the-art performance of interpretable models on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-07-30T03:37:00Z)
• Towards robust vision by multi-task learning on monkey visual cortex [6.9014416935919565]
  We jointly trained a deep network to perform image classification and to predict neural activity in macaque primary visual cortex (V1) We found that co-training on monkey V1 data leads to increased robustness despite the absence of those distortions during training. Our results also demonstrated that the network's representations become more brain-like as their robustness improves.
  arXiv  Detail & Related papers  (2021-07-29T21:55:48Z)
• Learning distinct features helps, provably [98.78384185493624]
  We study the diversity of the features learned by a two-layer neural network trained with the least squares loss. We measure the diversity by the average $L$-distance between the hidden-layer features.
  arXiv  Detail & Related papers  (2021-06-10T19:14:45Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition [77.95361323613147]
  Current state-of-the-art visual recognition systems rely on pretraining a neural network on a large-scale dataset and finetuning the network weights on a smaller dataset. In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness. Our method can be easily generalized to an unsupervised paradigm by replacing supernet training with self-supervised learning in the source domain tasks and performing linear evaluation in the downstream tasks.
  arXiv  Detail & Related papers  (2021-03-31T08:15:17Z)
• Architecture Agnostic Neural Networks [33.803822613725984]
  We create families of architecture agnostic neural networks not trained via backpropagation. These high-performing network families share the same sparsity, distribution of binary weights, and succeed in both static and dynamic tasks.
  arXiv  Detail & Related papers  (2020-11-05T09:04:07Z)

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.