This Probably Looks Exactly Like That: An Invertible Prototypical Network

• URL: http://arxiv.org/abs/2407.12200v1
• Date: Tue, 16 Jul 2024 21:51:02 GMT
• Title: This Probably Looks Exactly Like That: An Invertible Prototypical Network
• Authors: Zachariah Carmichael, Timothy Redgrave, Daniel Gonzalez Cedre, Walter J. Scheirer,
• Abstract summary: Prototypical neural networks represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models.
• Score: 8.957872207471311
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural network, represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations, but a human-machine semantic gap continues to haunt current approaches. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. From this, we posit that invertibly learning prototypes as distributions over the latent space provides more robust, expressive, and interpretable modeling. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models. ProtoFlow (1) sets a new state-of-the-art in joint generative and predictive modeling and (2) achieves predictive performance comparable to existing prototypical neural networks while enabling richer interpretation.

Related papers

• 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)
• Distilling Symbolic Priors for Concept Learning into Neural Networks [9.915299875869046]
  We show that inductive biases can be instantiated in artificial neural networks by distilling a prior distribution from a symbolic Bayesian model via meta-learning. We use this approach to create a neural network with an inductive bias towards concepts expressed as short logical formulas.
  arXiv  Detail & Related papers  (2024-02-10T20:06:26Z)
• Manipulating Feature Visualizations with Gradient Slingshots [54.31109240020007]
  We introduce a novel method for manipulating Feature Visualization (FV) without significantly impacting the model's decision-making process. We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons.
  arXiv  Detail & Related papers  (2024-01-11T18:57:17Z)
• Instance-wise Linearization of Neural Network for Model Interpretation [13.583425552511704]
  The challenge can dive into the non-linear behavior of the neural network. For a neural network model, the non-linear behavior is often caused by non-linear activation units of a model. We propose an instance-wise linearization approach to reformulates the forward computation process of a neural network prediction.
  arXiv  Detail & Related papers  (2023-10-25T02:07:39Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• Hybrid machine-learned homogenization: Bayesian data mining and convolutional neural networks [0.0]
  This study aims to improve the machine learned prediction by developing novel feature descriptors. The iterative development of feature descriptors resulted in 37 novel features, being able to reduce the prediction error by roughly one third. A combination of the feature based approach and the convolutional neural network leads to a hybrid neural network.
  arXiv  Detail & Related papers  (2023-02-24T09:59:29Z)
• 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)
• ExSpliNet: An interpretable and expressive spline-based neural network [0.3867363075280544]
  We present ExSpliNet, an interpretable and expressive neural network model. We give a probabilistic interpretation of the model and show its universal approximation properties.
  arXiv  Detail & Related papers  (2022-05-03T14:06:36Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• 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)
• Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model [35.341634678764066]
  Humans have the ability to rapidly understand rich concepts from limited data. We propose a neuro-symbolic generative model which combines the strengths of previous approaches to concept learning.
  arXiv  Detail & Related papers  (2021-04-16T17:57:51Z)

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.