SensLI: Sensitivity-Based Layer Insertion for Neural Networks

• URL: http://arxiv.org/abs/2311.15995v2
• Date: Mon, 16 Jun 2025 21:12:13 GMT
• Title: SensLI: Sensitivity-Based Layer Insertion for Neural Networks
• Authors: Leonie Kreis, Evelyn Herberg, Frederik Köhne, Anton Schiela, Roland Herzog,
• Abstract summary: We propose a systematic approach to inserting new layers during the training process of neural networks.<n>Our method eliminates the need to choose a fixed network size before training.<n>Our proposed sensitivity-based layer insertion technique (SensLI) exhibits improved performance on training loss and test error.
• Score: 0.36157708183789494
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The training of neural networks requires tedious and often manual tuning of the network architecture. We propose a systematic approach to inserting new layers during the training process. Our method eliminates the need to choose a fixed network size before training, is numerically inexpensive to execute and applicable to various architectures including fully connected feedforward networks, ResNets and CNNs. Our technique borrows ideas from constrained optimization and is based on first-order sensitivity information of the loss function with respect to the virtual parameters that additional layers, if inserted, would offer. In numerical experiments, our proposed sensitivity-based layer insertion technique (SensLI) exhibits improved performance on training loss and test error, compared to training on a fixed architecture, and reduced computational effort in comparison to training the extended architecture from the beginning. Our code is available on https://github.com/mathemml/SensLI.

Related papers

• Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy [0.0]
  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.
  arXiv  Detail & Related papers  (2024-06-13T18:00:05Z)
• Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them [0.0]
  Traditional approaches to neuroevolution often start from scratch. Recombining trained networks is non-trivial because architectures and feature representations typically differ. We employ stitching, which merges the networks by introducing new layers at crossover points.
  arXiv  Detail & Related papers  (2024-03-21T08:30:44Z)
• NeuralFastLAS: Fast Logic-Based Learning from Raw Data [54.938128496934695]
  Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically. Neuro-symbolic approaches overcome this issue by mapping raw data to latent symbolic concepts using a neural network. We introduce NeuralFastLAS, a scalable and fast end-to-end approach that trains a neural network jointly with a symbolic learner.
  arXiv  Detail & Related papers  (2023-10-08T12:33:42Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Breaking the Architecture Barrier: A Method for Efficient Knowledge Transfer Across Networks [0.0]
  We present a method for transferring parameters between neural networks with different architectures. Our method, called DPIAT, uses dynamic programming to match blocks and layers between architectures and transfer parameters efficiently. In experiments on ImageNet, our method improved validation accuracy by an average of 1.6 times after 50 epochs of training.
  arXiv  Detail & Related papers  (2022-12-28T17:35:41Z)
• Towards Theoretically Inspired Neural Initialization Optimization [66.04735385415427]
  We propose a differentiable quantity, named GradCosine, with theoretical insights to evaluate the initial state of a neural network. We show that both the training and test performance of a network can be improved by maximizing GradCosine under norm constraint. Generalized from the sample-wise analysis into the real batch setting, NIO is able to automatically look for a better initialization with negligible cost.
  arXiv  Detail & Related papers  (2022-10-12T06:49:16Z)
• Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization [1.3999481573773072]
  We introduce and evaluate the batch-entropy which quantifies the flow of information through each layer of a neural network. We show that we can train a "vanilla" fully connected network and convolutional neural network with 500 layers by simply adding the batch-entropy regularization term to the loss function.
  arXiv  Detail & Related papers  (2022-08-01T20:31:58Z)
• Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring [87.97330195531029]
  We propose a Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data. The proposed NeurMAP is an approach to existing deblurring neural networks, and is the first framework that enables training image deblurring networks on unpaired datasets.
  arXiv  Detail & Related papers  (2022-04-26T08:09:47Z)
• Backward Gradient Normalization in Deep Neural Networks [68.8204255655161]
  We introduce a new technique for gradient normalization during neural network training. The gradients are rescaled during the backward pass using normalization layers introduced at certain points within the network architecture. Results on tests with very deep neural networks show that the new technique can do an effective control of the gradient norm.
  arXiv  Detail & Related papers  (2021-06-17T13:24:43Z)
• Auto-tuning of Deep Neural Networks by Conflicting Layer Removal [0.0]
  We introduce a novel methodology to identify layers that decrease the test accuracy of trained models. Conflicting layers are detected as early as the beginning of training. We will show that around 60% of the layers of trained residual networks can be completely removed from the architecture.
  arXiv  Detail & Related papers  (2021-03-07T11:51:55Z)
• 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)
• Learning Neural Network Subspaces [74.44457651546728]
  Recent observations have advanced our understanding of the neural network optimization landscape. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks.
  arXiv  Detail & Related papers  (2021-02-20T23:26:58Z)
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training [59.160154997555956]
  We present GradInit, an automated and architecture method for initializing neural networks. It is based on a simple agnostic; the variance of each network layer is adjusted so that a single step of SGD or Adam results in the smallest possible loss value. It also enables training the original Post-LN Transformer for machine translation without learning rate warmup.
  arXiv  Detail & Related papers  (2021-02-16T11:45:35Z)
• Local Critic Training for Model-Parallel Learning of Deep Neural Networks [94.69202357137452]
  We propose a novel model-parallel learning method, called local critic training. We show that the proposed approach successfully decouples the update process of the layer groups for both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) We also show that trained networks by the proposed method can be used for structural optimization.
  arXiv  Detail & Related papers  (2021-02-03T09:30:45Z)
• LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks [15.373764014931792]
  LOss-Based SensiTivity rEgulaRization is a method for training neural networks with a sparse topology. Our method allows to train a network from scratch, i.e. without preliminary learning or rewinding.
  arXiv  Detail & Related papers  (2020-11-16T18:55:34Z)
• Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks [1.7188280334580195]
  We introduce a novel theory and metric to identify layers that decrease the test accuracy of the trained models. We identify those layers that worsen the performance because they produce conflicting training bundles. Based on these findings, a novel algorithm is introduced to remove performance decreasing layers automatically.
  arXiv  Detail & Related papers  (2020-11-05T16:41:04Z)
• A ReLU Dense Layer to Improve the Performance of Neural Networks [40.2470651460466]
  We propose ReDense as a simple and low complexity way to improve the performance of trained neural networks. We experimentally show that ReDense can improve the training and testing performance of various neural network architectures.
  arXiv  Detail & Related papers  (2020-10-22T11:56:01Z)
• MSE-Optimal Neural Network Initialization via Layer Fusion [68.72356718879428]
  Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks. The use of gradient combined nonvolutionity renders learning susceptible to novel problems. We propose fusing neighboring layers of deeper networks that are trained with random variables.
  arXiv  Detail & Related papers  (2020-01-28T18:25:15Z)

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.