Layerwise Change of Knowledge in Neural Networks
- URL: http://arxiv.org/abs/2409.08712v1
- Date: Fri, 13 Sep 2024 10:59:24 GMT
- Title: Layerwise Change of Knowledge in Neural Networks
- Authors: Xu Cheng, Lei Cheng, Zhaoran Peng, Yang Xu, Tian Han, Quanshi Zhang,
- Abstract summary: This paper aims to explain how a deep neural network gradually extracts new knowledge and forgets noisy features through layers in forward propagation.
We quantify and track the newly emerged interactions and the forgotten interactions in each layer during the forward propagation.
- Score: 25.919449855059415
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper aims to explain how a deep neural network (DNN) gradually extracts new knowledge and forgets noisy features through layers in forward propagation. Up to now, although the definition of knowledge encoded by the DNN has not reached a consensus, Previous studies have derived a series of mathematical evidence to take interactions as symbolic primitive inference patterns encoded by a DNN. We extend the definition of interactions and, for the first time, extract interactions encoded by intermediate layers. We quantify and track the newly emerged interactions and the forgotten interactions in each layer during the forward propagation, which shed new light on the learning behavior of DNNs. The layer-wise change of interactions also reveals the change of the generalization capacity and instability of feature representations of a DNN.
Related papers
- Towards the Dynamics of a DNN Learning Symbolic Interactions [20.493304123269446]
In recent years, a series of theorems have been proven to show that given an input sample, a small number of interactions between input variables can be considered as primitive inference patterns.
This study proves the two-phase dynamics of a deep neural network (DNN) learning interactions.
arXiv Detail & Related papers (2024-07-27T07:34:49Z) - Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features [68.3512123520931]
We investigate the dynamics of a deep neural network (DNN) learning interactions.
In this paper, we discover the DNN learns interactions in two phases.
The first phase mainly penalizes interactions of medium and high orders, and the second phase mainly learns interactions of gradually increasing orders.
arXiv Detail & Related papers (2024-05-16T17:13:25Z) - Defining and Extracting generalizable interaction primitives from DNNs [22.79131582164054]
We develop a new method to extract interactions that are shared by different deep neural networks (DNNs)
Experiments show that the extracted interactions can better reflect common knowledge shared by different DNNs.
arXiv Detail & Related papers (2024-01-29T17:21:41Z) - Domain-informed graph neural networks: a quantum chemistry case study [0.34410212782758054]
We focus on graph neural networks (GNN), with a use case of estimating the potential energy of chemical systems (molecules and crystals) represented as graphs.
We integrate two elements of domain knowledge into the design of the GNN to constrain and regularise its learning, towards higher accuracy and generalisation.
arXiv Detail & Related papers (2022-08-25T08:36:50Z) - Knowledge Enhanced Neural Networks for relational domains [83.9217787335878]
We focus on a specific method, KENN, a Neural-Symbolic architecture that injects prior logical knowledge into a neural network.
In this paper, we propose an extension of KENN for relational data.
arXiv Detail & Related papers (2022-05-31T13:00:34Z) - Deep Architecture Connectivity Matters for Its Convergence: A
Fine-Grained Analysis [94.64007376939735]
We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training.
We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
arXiv Detail & Related papers (2022-05-11T17:43:54Z) - Examining the causal structures of deep neural networks using
information theory [0.0]
Deep Neural Networks (DNNs) are often examined at the level of their response to input, such as analyzing the mutual information between nodes and data sets.
DNNs can also be examined at the level of causation, exploring "what does what" within the layers of the network itself.
Here, we introduce a suite of metrics based on information theory to quantify and track changes in the causal structure of DNNs during training.
arXiv Detail & Related papers (2020-10-26T19:53:16Z) - Neural Networks Enhancement with Logical Knowledge [83.9217787335878]
We propose an extension of KENN for relational data.
The results show that KENN is capable of increasing the performances of the underlying neural network even in the presence relational data.
arXiv Detail & Related papers (2020-09-13T21:12:20Z) - Progressive Tandem Learning for Pattern Recognition with Deep Spiking
Neural Networks [80.15411508088522]
Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency.
We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
arXiv Detail & Related papers (2020-07-02T15:38:44Z) - Architecture Disentanglement for Deep Neural Networks [174.16176919145377]
We introduce neural architecture disentanglement (NAD) to explain the inner workings of deep neural networks (DNNs)
NAD learns to disentangle a pre-trained DNN into sub-architectures according to independent tasks, forming information flows that describe the inference processes.
Results show that misclassified images have a high probability of being assigned to task sub-architectures similar to the correct ones.
arXiv Detail & Related papers (2020-03-30T08:34:33Z)
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.