RK
R.F. Klazinga
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
Autoencoders seek to encode their input into a bottleneck of latent neurons, and then decode it to reconstruct the input. However, if the input data has an intrinsic dimension (ID) smaller than the number of latent neurons in the bottleneck, this encoding becomes redundant.
In this paper, we study using the Early-Bird (EB) technique, a structural pruning method, to regularise and prune the redundant latent neurons. We do this for both linear-layer and convolutional autoencoders, on 1D and 2D data. We find that increasing the strength of EB regularisation specifically on the latent layer can lead to all redundant latent neurons (and no more) being removed in one training run.
We also compare using EB in this manner to existing ID estimation methods: we find it performs comparable to older methods like local-PCA, also being relatively robust to noise, but that it does not match the best existing ID estimation methods. ...
In this paper, we study using the Early-Bird (EB) technique, a structural pruning method, to regularise and prune the redundant latent neurons. We do this for both linear-layer and convolutional autoencoders, on 1D and 2D data. We find that increasing the strength of EB regularisation specifically on the latent layer can lead to all redundant latent neurons (and no more) being removed in one training run.
We also compare using EB in this manner to existing ID estimation methods: we find it performs comparable to older methods like local-PCA, also being relatively robust to noise, but that it does not match the best existing ID estimation methods. ...
Autoencoders seek to encode their input into a bottleneck of latent neurons, and then decode it to reconstruct the input. However, if the input data has an intrinsic dimension (ID) smaller than the number of latent neurons in the bottleneck, this encoding becomes redundant.
In this paper, we study using the Early-Bird (EB) technique, a structural pruning method, to regularise and prune the redundant latent neurons. We do this for both linear-layer and convolutional autoencoders, on 1D and 2D data. We find that increasing the strength of EB regularisation specifically on the latent layer can lead to all redundant latent neurons (and no more) being removed in one training run.
We also compare using EB in this manner to existing ID estimation methods: we find it performs comparable to older methods like local-PCA, also being relatively robust to noise, but that it does not match the best existing ID estimation methods.
In this paper, we study using the Early-Bird (EB) technique, a structural pruning method, to regularise and prune the redundant latent neurons. We do this for both linear-layer and convolutional autoencoders, on 1D and 2D data. We find that increasing the strength of EB regularisation specifically on the latent layer can lead to all redundant latent neurons (and no more) being removed in one training run.
We also compare using EB in this manner to existing ID estimation methods: we find it performs comparable to older methods like local-PCA, also being relatively robust to noise, but that it does not match the best existing ID estimation methods.
Bachelor thesis
(2020)
-
J. Haas, R.F. Klazinga, N. van Stijn, J. Teunissen, Y. Zhang, M. Loog, Eelko Ronner, O.W. Visser
The core challenge of the BedBasedEcho BEP project is to create an algorithm to find the heart, and apply it on a robotic echocardiography solution. The team has found multiple complex solutions that are related to this problem, and has extracted useful information from these solutions to apply to this problem. However, some of these complex solutions were too complex, causing the team to run out of physical resources, or to have the solution fail entirely. By taking a step back, and simplifying the solution, the team has managed to create a system that performs marginally better than the complex solutions. The designed product consists of three major components: the data gathering, the learning, and the deployment. When used in this order, the result is an algorithm that can predict which way it should move to gain the optimal view of the heart. The algorithm will be used as a component in a larger automated echocardiography system. Ultimately, the algorithm showed promise by autonomously finding a good view of the heart.
...
The core challenge of the BedBasedEcho BEP project is to create an algorithm to find the heart, and apply it on a robotic echocardiography solution. The team has found multiple complex solutions that are related to this problem, and has extracted useful information from these solutions to apply to this problem. However, some of these complex solutions were too complex, causing the team to run out of physical resources, or to have the solution fail entirely. By taking a step back, and simplifying the solution, the team has managed to create a system that performs marginally better than the complex solutions. The designed product consists of three major components: the data gathering, the learning, and the deployment. When used in this order, the result is an algorithm that can predict which way it should move to gain the optimal view of the heart. The algorithm will be used as a component in a larger automated echocardiography system. Ultimately, the algorithm showed promise by autonomously finding a good view of the heart.