Increasing biases can be more efficient than increasing weights

• URL: http://arxiv.org/abs/2301.00924v3
• Date: Thu, 18 Jan 2024 06:13:12 GMT
• Title: Increasing biases can be more efficient than increasing weights
• Authors: Carlo Metta, Marco Fantozzi, Andrea Papini, Gianluca Amato, Matteo Bergamaschi, Silvia Giulia Galfr\`e, Alessandro Marchetti, Michelangelo Vegli\`o, Maurizio Parton, Francesco Morandin
• Abstract summary: Unit emphasizes the importance of preserving uncorrupted information as it is passed from one unit to the next. We show that by focusing on increasing biases rather than weights, there is potential for significant enhancement in a neural network model's performance.
• Score: 33.05856234084821
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce a novel computational unit for neural networks that features multiple biases, challenging the traditional perceptron structure. This unit emphasizes the importance of preserving uncorrupted information as it is passed from one unit to the next, applying activation functions later in the process with specialized biases for each unit. Through both empirical and theoretical analyses, we show that by focusing on increasing biases rather than weights, there is potential for significant enhancement in a neural network model's performance. This approach offers an alternative perspective on optimizing information flow within neural networks. See source code at https://github.com/CuriosAI/dac-dev.

Related papers

• Interpreting Neural Networks through Mahalanobis Distance [0.0]
  This paper introduces a theoretical framework that connects neural network linear layers with the Mahalanobis distance. Although this work is theoretical and does not include empirical data, the proposed distance-based interpretation has the potential to enhance model robustness, improve generalization, and provide more intuitive explanations of neural network decisions.
  arXiv  Detail & Related papers  (2024-10-25T07:21:44Z)
• Expressivity of Neural Networks with Random Weights and Learned Biases [44.02417750529102]
  Recent work has pushed the bounds of universal approximation by showing that arbitrary functions can similarly be learned by tuning smaller subsets of parameters. We provide theoretical and numerical evidence demonstrating that feedforward neural networks with fixed random weights can be trained to perform multiple tasks by learning biases only. Our results are relevant to neuroscience, where they demonstrate the potential for behaviourally relevant changes in dynamics without modifying synaptic weights.
  arXiv  Detail & Related papers  (2024-07-01T04:25:49Z)
• Towards Scalable and Versatile Weight Space Learning [51.78426981947659]
  This paper introduces the SANE approach to weight-space learning. Our method extends the idea of hyper-representations towards sequential processing of subsets of neural network weights.
  arXiv  Detail & Related papers  (2024-06-14T13:12:07Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• Look beyond labels: Incorporating functional summary information in Bayesian neural networks [11.874130244353253]
  We present a simple approach to incorporate summary information about the predicted probability. The available summary information is incorporated as augmented data and modeled with a Dirichlet process. We show how the method can inform the model about task difficulty or class imbalance.
  arXiv  Detail & Related papers  (2022-07-04T07:06:45Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Fast Adaptation with Linearized Neural Networks [35.43406281230279]
  We study the inductive biases of linearizations of neural networks, which we show to be surprisingly good summaries of the full network functions. Inspired by this finding, we propose a technique for embedding these inductive biases into Gaussian processes through a kernel designed from the Jacobian of the network. In this setting, domain adaptation takes the form of interpretable posterior inference, with accompanying uncertainty estimation.
  arXiv  Detail & Related papers  (2021-03-02T03:23:03Z)
• Infinite-dimensional Folded-in-time Deep Neural Networks [0.0]
  In this work, we present an infinite-dimensional generalization, which allows for a more rigorous mathematical analysis. We also provide a functional backpropagation algorithm, which enables descent training of the weights.
  arXiv  Detail & Related papers  (2021-01-08T11:30:50Z)

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.