Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy

• URL: http://arxiv.org/abs/2406.12916v2
• Date: Fri, 9 Aug 2024 08:08:42 GMT
• Title: Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy
• Authors: Yanick Thurn, Ro Jefferson, Johanna Erdmenger,
• Abstract summary: We present a method for predicting the trainable regime in parameter space for deep feedforward neural networks. For both the MNIST and CIFAR10 datasets, we show that a single epoch of training is sufficient to predict the trainability of the deep feedforward network.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An important challenge in machine learning is to predict the initial conditions under which a given neural network will be trainable. We present a method for predicting the trainable regime in parameter space for deep feedforward neural networks, based on reconstructing the input from subsequent activation layers via a cascade of single-layer auxiliary networks. For both the MNIST and CIFAR10 datasets, we show that a single epoch of training of the shallow cascade networks is sufficient to predict the trainability of the deep feedforward network, thereby providing a significant reduction in overall training time. We achieve this by computing the relative entropy between reconstructed images and the original inputs, and show that this probe of information loss is sensitive to the phase behaviour of the network. Moreover, our approach illustrates the network's decision making process by displaying the changes performed on the input data at each layer. Our results provide a concrete link between the flow of information and the trainability of deep neural networks, further explaining the role of criticality in these systems.

Related papers

• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• 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)
• Reconstructing Training Data from Trained Neural Networks [42.60217236418818]
  We show in some cases a significant fraction of the training data can in fact be reconstructed from the parameters of a trained neural network classifier. We propose a novel reconstruction scheme that stems from recent theoretical results about the implicit bias in training neural networks with gradient-based methods.
  arXiv  Detail & Related papers  (2022-06-15T18:35:16Z)
• Decomposing neural networks as mappings of correlation functions [57.52754806616669]
  We study the mapping between probability distributions implemented by a deep feed-forward network. We identify essential statistics in the data, as well as different information representations that can be used by neural networks.
  arXiv  Detail & Related papers  (2022-02-10T09:30:31Z)
• 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)
• Clustering-Based Interpretation of Deep ReLU Network [17.234442722611803]
  We recognize that the non-linear behavior of the ReLU function gives rise to a natural clustering. We propose a method to increase the level of interpretability of a fully connected feedforward ReLU neural network.
  arXiv  Detail & Related papers  (2021-10-13T09:24:11Z)
• Semi-supervised Network Embedding with Differentiable Deep Quantisation [81.49184987430333]
  We develop d-SNEQ, a differentiable quantisation method for network embedding. d-SNEQ incorporates a rank loss to equip the learned quantisation codes with rich high-order information. It is able to substantially compress the size of trained embeddings, thus reducing storage footprint and accelerating retrieval speed.
  arXiv  Detail & Related papers  (2021-08-20T11:53:05Z)
• The distance between the weights of the neural network is meaningful [9.329400348695435]
  In the application of neural networks, we need to select a suitable model based on the problem complexity and the dataset scale. This paper proves that the distance between the neural network weights in different training stages can be used to estimate the information accumulated by the network in the training process directly.
  arXiv  Detail & Related papers  (2021-01-31T06:44:49Z)
• Implicit recurrent networks: A novel approach to stationary input processing with recurrent neural networks in deep learning [0.0]
  In this work, we introduce and test a novel implementation of recurrent neural networks into deep learning. We provide an algorithm which implements the backpropagation algorithm on a implicit implementation of recurrent networks. A single-layer implicit recurrent network is able to solve the XOR problem, while a feed-forward network with monotonically increasing activation function fails at this task.
  arXiv  Detail & Related papers  (2020-10-20T18:55:32Z)
• Compact Neural Representation Using Attentive Network Pruning [1.0152838128195465]
  We describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subsequently prune redundant ones at all parametric layers. Our method not only introduces a novel hierarchical selection mechanism as the basis of pruning but also remains competitive with previous baseline methods in the experimental evaluation.
  arXiv  Detail & Related papers  (2020-05-10T03:20:01Z)
• Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations [143.3053365553897]
  We describe a procedure for removing dependency on a cohort of training data from a trained deep network. We introduce a new bound on how much information can be extracted per query about the forgotten cohort. We exploit the connections between the activation and weight dynamics of a DNN inspired by Neural Tangent Kernels to compute the information in the activations.
  arXiv  Detail & Related papers  (2020-03-05T23:17:35Z)

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.