| 1. |
- Aarrestad, Thea, et al.
(författare)
-
Fast convolutional neural networks on FPGAs with hls4ml
- 2021
-
Ingår i: Machine Learning: Science and Technology. - : IOP Publishing. - 2632-2153. ; 2:4
-
Tidskriftsartikel (refereegranskat)abstract
- We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on field-programmable gate arrays (FPGAs). By extending the hls4ml library, we demonstrate an inference latency of 5 mu s using convolutional architectures, targeting microsecond latency applications like those at the CERN Large Hadron Collider. Considering benchmark models trained on the Street View House Numbers Dataset, we demonstrate various methods for model compression in order to fit the computational constraints of a typical FPGA device used in trigger and data acquisition systems of particle detectors. In particular, we discuss pruning and quantization-aware training, and demonstrate how resource utilization can be significantly reduced with little to no loss in model accuracy. We show that the FPGA critical resource consumption can be reduced by 97% with zero loss in model accuracy, and by 99% when tolerating a 6% accuracy degradation.
|
|
| 2. |
- Anderson, Louise, 1989, et al.
(författare)
-
The trouble with twisting (2,0) theory
- 2014
-
Ingår i: Journal of High Energy Physics. - 1029-8479 .- 1126-6708. ; 2014:3, s. Art. no. 062-
-
Tidskriftsartikel (refereegranskat)abstract
- We consider a twisted version of the abelian (2,0) theory placed upon a Lorenzian six-manifold with a product structure, M_6=C×M_4. This is done by an investigation of the free tensor multiplet on the level of equations of motion, where the problem of its formulation in Euclidean signature is circumvented by letting the time-like direction lie in the two-manifold C and performing a topological twist along M_4 alone. A compactification on C is shown to be necessary to enable the possibility of finding a topological field theory. The hypothetical twist along a Euclidean C is argued to amount to the correct choice of linear combination of the two supercharges scalar on M_4. It may be slightly surprising that this is not the same linear combination as in the well known Donaldson-Witten twist. A more surprising fact however, is that this twisted theory contains no Q-exact and covariantly conserved stress tensor unless M_4 has vanishing curvature. This is to our knowledge a phenomenon which has not been observed before in topological field theories. In the literature, the setup of the twisting used here has been suggested as the origin of the conjectured AGT-correspondence, and our hope is that this work may somehow contribute to the understanding of it.
|
|
| 3. |
- Balabanov, Oleksandr, et al.
(författare)
-
Bayesian Posterior Approximation With Stochastic Ensembles
- 2023
-
Ingår i: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. - 1063-6919. - 9798350301298 ; 2023-June, s. 13701-13711
-
Konferensbidrag (refereegranskat)abstract
- We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochas-tic ensembles are formulated as families of distributions and trained to approximate the Bayesian posterior with variational inference. We implement stochastic ensembles based on Monte Carlo dropout, DropConnect and a novel non-parametric version of dropout and evaluate them on a toy problem and CIFAR image classification. For both tasks, we test the quality of the posteriors directly against Hamil-tonian Monte Carlo simulations. Our results show that stochastic ensembles provide more accurate posterior esti-mates than other popular baselines for Bayesian inference.
|
|
| 4. |
- Gerken, Jan, 1991, et al.
(författare)
-
Equivariance versus augmentation for spherical images
- 2022
-
Ingår i: Proceedings of Machine Learning Resaerch. ; , s. 7404-7421
-
Konferensbidrag (refereegranskat)abstract
- We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with an increasing amount of data augmentation. The chosen architectures can be considered baseline references for the respective design paradigms. Our models are trained and evaluated on single or multiple items from the MNIST- or FashionMNIST dataset projected onto the sphere. For the task of image classification, which is inherently rotationally invariant, we find that by considerably increasing the amount of data augmentation and the size of the networks, it is possible for the standard CNNs to reach at least the same performance as the equivariant network. In contrast, for the inherently equivariant task of semantic segmentation, the non-equivariant networks are consistently outperformed by the equivariant networks with significantly fewer parameters. We also analyze and compare the inference latency and training times of the different networks, enabling detailed tradeoff considerations between equivariant architectures and data augmentation for practical problems.
|
|
| 5. |
- Gerken, Jan, 1991, et al.
(författare)
-
Geometric deep learning and equivariant neural networks
- 2023
-
Ingår i: Artificial Intelligence Review. - : Springer Nature. - 1573-7462 .- 0269-2821. ; 56:12, s. 14605-14662
-
Tidskriftsartikel (refereegranskat)abstract
- We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds M using principal bundles with structure group K and equivariant maps between sections of associated vector bundles. We also discuss group equivariant neural networks for homogeneous spaces M= G/ K , which are instead equivariant with respect to the global symmetry G on M . Group equivariant layers can be interpreted as intertwiners between induced representations of G, and we show their relation to gauge equivariant convolutional layers. We analyze several applications of this formalism, including semantic segmentation and object detection networks. We also discuss the case of spherical networks in great detail, corresponding to the case M= S2= SO (3) / SO (2) . Here we emphasize the use of Fourier analysis involving Wigner matrices, spherical harmonics and Clebsch–Gordan coefficients for G= SO (3) , illustrating the power of representation theory for deep learning.
|
|
| 6. |
- Ghielmetti, N., et al.
(författare)
-
Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml
- 2022
-
Ingår i: Machine Learning - Science and Technology. - : IOP Publishing. - 2632-2153. ; 3:4
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network architecture, we demonstrate a fully-on-chip deployment with a latency of 4.9 ms per image, using less than 30% of the available resources on a Xilinx ZCU102 evaluation board. The latency is reduced to 3 ms per image when increasing the batch size to ten, corresponding to the use case where the autonomous vehicle receives inputs from multiple cameras simultaneously. We show, through aggressive filter reduction and heterogeneous quantization-aware training, and an optimized implementation of convolutional layers, that the power consumption and resource utilization can be significantly reduced while maintaining accuracy on the Cityscapes dataset.
|
|
| 7. |
- Gran, Ulf, 1973, et al.
(författare)
-
Off-shell structure of twisted (2,0) theory
- 2014
-
Ingår i: Journal of High Energy Physics. - 1029-8479 .- 1126-6708. ; 2014:11
-
Tidskriftsartikel (refereegranskat)abstract
- A $Q$-exact off-shell action is constructed for twisted abelian (2,0) theory on a Lorentzian six-manifold of the form $M_{1,5} = C\times M_4$, where $C$ is a flat two-manifold and $M_4$ is a general Euclidean four-manifold. The properties of this formulation, which is obtained by introducing two auxiliary fields, can be summarised by a commutative diagram where the Lagrangian and its stress-tensor arise from the $Q$-variation of two fermionic quantities $V$ and $\lambda^{\mu\nu}$. This completes and extends the analysis in [arXiv:1311.3300].
|
|
| 8. |
- Linander, Hampus, 1985
(författare)
-
(2,0) Theory and Higher Spin: Twisting, Turning and Spinning Towards Higher Energies
- 2016
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis investigates an enigmatic six-dimensional quantum theory known as (2,0) theory and a three dimensional conformal theory of higher spin. The former has resisted an explicit construction as a quantum field theory, yet its existence can be inferred from string theory and M-theory where it plays a prominent role. Theories of higher spin, only recently emerging with consistent formulations, also have intricate connections with string theory where they might provide insight into the high energy behaviour and have recently played an important part in holographic dualities. A deeper understanding of these theories is therefore an important challange that promise to provide new insight into string theory and the mathematical framework of theoretical physics in general.First the six dimensional (2,0) theory is investigated in terms of an explicit formulation of one free tensor multiplet on circle fibrations. The fibration geometry provides additional data in a compactification to five dimensions used to derive an interacting generalization. Topological twisting of the tensor multiplet is then carried out, resulting in an off-shell formulation making use of the Q-cohomology structure.The second part of the thesis concerns conformal higher spin in three dimensions, constructed as an extension of the gauge theory formulation of gravity. Using a computer tensor algebra system developed for this purpose, the full non-linear system is solved at the spin 3 level.
|
|
| 9. |
- Linander, Hampus, 1985, et al.
(författare)
-
(2,0) theory on circle fibrations
- 2012
-
Ingår i: Journal of High Energy Physics. - 1029-8479 .- 1126-6708. ; 2012:1, s. Article Number: 159 -
-
Tidskriftsartikel (refereegranskat)abstract
- We consider (2,0) theory on a manifold M_6 that is a fibration of a spatial S^1 over some five-dimensional base manifold M_5. Initially, we study the free (2,0) tensor multiplet which can be described in terms of classical equations of motion in six dimensions. Given a metric on M_6 the low energy effective theory obtained through dimensional reduction on the circle is a Maxwell theory on M_5. The parameters describing the local geometry of the fibration are interpreted respectively as the metric on M_5, a non-dynamical U(1) gauge field and the coupling strength of the resulting low energy Maxwell theory. We derive the general form of the action of the Maxwell theory by integrating the reduced equations of motion, and consider the symmetries of this theory originating from the superconformal symmetry in six dimensions. Subsequently, we consider a non-abelian generalization of the Maxwell theory on M_5. Completing the theory with Yukawa and phi^4 terms, and suitably modifying the supersymmetry transformations, we obtain a supersymmetric Yang-Mills theory which includes terms related to the geometry of the fibration.
|
|
| 10. |
- Linander, Hampus, 1985, et al.
(författare)
-
Looking at the posterior: accuracy and uncertainty of neural-network predictions
- 2023
-
Ingår i: Machine Learning: Science and Technology. - 2632-2153. ; 4:4
-
Tidskriftsartikel (refereegranskat)abstract
- Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output. By looking at these posterior distributions, one can separate the origin of uncertainty into aleatoric and epistemic contributions. One goal of uncertainty quantification is to inform on prediction accuracy. Here we show that prediction accuracy depends on both epistemic and aleatoric uncertainty in an intricate fashion that cannot be understood in terms of marginalized uncertainty distributions alone. How the accuracy relates to epistemic and aleatoric uncertainties depends not only on the model architecture, but also on the properties of the dataset. We discuss the significance of these results for active learning and introduce a novel acquisition function that outperforms common uncertainty-based methods. To arrive at our results, we approximated the posteriors using deep ensembles, for fully-connected, convolutional and attention-based neural networks.
|
|
