Explaining Deep Learning Representations by Tracing the Training Process
- URL: http://arxiv.org/abs/2109.05880v1
- Date: Mon, 13 Sep 2021 11:29:04 GMT
- Title: Explaining Deep Learning Representations by Tracing the Training Process
- Authors: Lukas Pfahler, Katharina Morik
- Abstract summary: We propose a novel explanation method that explains the decisions of a deep neural network.
We investigate how the intermediate representations at each layer of the deep network were refined during the training process.
We show that our method identifies highly representative training instances that can be used as an explanation.
- Score: 10.774699463547439
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a novel explanation method that explains the decisions of a deep
neural network by investigating how the intermediate representations at each
layer of the deep network were refined during the training process. This way we
can a) find the most influential training examples during training and b)
analyze which classes attributed most to the final representation. Our method
is general: it can be wrapped around any iterative optimization procedure and
covers a variety of neural network architectures, including feed-forward
networks and convolutional neural networks. We first propose a method for
stochastic training with single training instances, but continue to also derive
a variant for the common mini-batch training. In experimental evaluations, we
show that our method identifies highly representative training instances that
can be used as an explanation. Additionally, we propose a visualization that
provides explanations in the form of aggregated statistics over the whole
training process.
Related papers
- A Quantitative Approach to Predicting Representational Learning and
Performance in Neural Networks [5.544128024203989]
Key property of neural networks is how they learn to represent and manipulate input information in order to solve a task.
We introduce a new pseudo-kernel based tool for analyzing and predicting learned representations.
arXiv Detail & Related papers (2023-07-14T18:39:04Z) - Exploring Low Rank Training of Deep Neural Networks [49.18122605463354]
Training deep neural networks in low rank offers efficiency over unfactorised training in terms of both memory consumption and training time.
We analyse techniques that work well in practice, and through extensive ablations on models such as GPT2 we provide evidence falsifying common beliefs in the field.
arXiv Detail & Related papers (2022-09-27T17:43:45Z) - 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) - 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) - Being Friends Instead of Adversaries: Deep Networks Learn from Data
Simplified by Other Networks [23.886422706697882]
A different idea has been recently proposed, named Friendly Training, which consists in altering the input data by adding an automatically estimated perturbation.
We revisit and extend this idea inspired by the effectiveness of neural generators in the context of Adversarial Machine Learning.
We propose an auxiliary multi-layer network that is responsible of altering the input data to make them easier to be handled by the classifier.
arXiv Detail & Related papers (2021-12-18T16:59:35Z) - Targeted Gradient Descent: A Novel Method for Convolutional Neural
Networks Fine-tuning and Online-learning [9.011106198253053]
A convolutional neural network (ConvNet) is usually trained and then tested using images drawn from the same distribution.
To generalize a ConvNet to various tasks often requires a complete training dataset that consists of images drawn from different tasks.
We present Targeted Gradient Descent (TGD), a novel fine-tuning method that can extend a pre-trained network to a new task without revisiting data from the previous task.
arXiv Detail & Related papers (2021-09-29T21:22:09Z) - 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) - 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) - Teaching with Commentaries [108.62722733649542]
We propose a flexible teaching framework using commentaries and learned meta-information.
We find that commentaries can improve training speed and/or performance.
commentaries can be reused when training new models to obtain performance benefits.
arXiv Detail & Related papers (2020-11-05T18:52:46Z) - Subset Sampling For Progressive Neural Network Learning [106.12874293597754]
Progressive Neural Network Learning is a class of algorithms that incrementally construct the network's topology and optimize its parameters based on the training data.
We propose to speed up this process by exploiting subsets of training data at each incremental training step.
Experimental results in object, scene and face recognition problems demonstrate that the proposed approach speeds up the optimization procedure considerably.
arXiv Detail & Related papers (2020-02-17T18:57:33Z)
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.