FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks

• URL: http://arxiv.org/abs/2204.04511v1
• Date: Sat, 9 Apr 2022 16:41:53 GMT
• Title: FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks
• Authors: Aleksandar Doknic and Torsten M\"oller
• Abstract summary: We show how to explore high-dimensional landscape characteristics of neural networks. We generalize observations on small neural networks to more complex systems. An interactive dashboard opens up a number of possible application networks.
• Score: 77.34726150561087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their effective use in various fields, many aspects of neural networks are poorly understood. One important way to investigate the characteristics of neural networks is to explore the loss landscape. However, most models produce a high-dimensional non-convex landscape which is difficult to visualize. We discuss and extend existing visualization methods based on 1D- and 2D slicing with a novel method that approximates the actual loss landscape geometry by using charts with interpretable axes. Based on the assumption that observations on small neural networks can generalize to more complex systems and provide us with helpful insights, we focus on small models in the range of a few dozen weights, which enables computationally cheap experiments and the use of an interactive dashboard. We observe symmetries around the zero vector, the influence of different layers on the global landscape, the different weight sensitivities around a minimizer, and how gradient descent navigates high-loss obstacles. The user study resulted in an average SUS (System Usability Scale) score with suggestions for improvement and opened up a number of possible application scenarios, such as autoencoders and ensemble networks.

Related papers

• 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)
• Automatic Discovery of Visual Circuits [66.99553804855931]
  We explore scalable methods for extracting the subgraph of a vision model's computational graph that underlies recognition of a specific visual concept. We find that our approach extracts circuits that causally affect model output, and that editing these circuits can defend large pretrained models from adversarial attacks.
  arXiv  Detail & Related papers  (2024-04-22T17:00:57Z)
• 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)
• Neuro-Visualizer: An Auto-encoder-based Loss Landscape Visualization Method [4.981452040789784]
  We present a novel auto-encoder-based non-linear landscape visualization method called Neuro-Visualizer. Our findings show that Neuro-Visualizer outperforms other linear and non-linear baselines.
  arXiv  Detail & Related papers  (2023-09-26T01:10:16Z)
• Point-Cloud Deep Learning of Porous Media for Permeability Prediction [0.0]
  We propose a novel deep learning framework for predicting permeability of porous media from their digital images. We model the boundary between solid matrix and pore spaces as point clouds and feed them as inputs to a neural network based on the PointNet architecture.
  arXiv  Detail & Related papers  (2021-07-18T22:59:21Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• Topological obstructions in neural networks learning [67.8848058842671]
  We study global properties of the loss gradient function flow. We use topological data analysis of the loss function and its Morse complex to relate local behavior along gradient trajectories with global properties of the loss surface.
  arXiv  Detail & Related papers  (2020-12-31T18:53:25Z)
• Avoiding Spurious Local Minima in Deep Quadratic Networks [0.0]
  We characterize the landscape of the mean squared nonlinear error for networks with neural activation functions. We prove that deepized neural networks with quadratic activations benefit from similar landscape properties.
  arXiv  Detail & Related papers  (2019-12-31T22:31:11Z)

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.