dlcp21:abstracts
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
dlcp21:abstracts [22/06/2021 16:14] – [Performance of convolutional neural networks processing simulated IACT images in the TAIGA experiment] admin | dlcp21:abstracts [22/06/2021 19:54] (current) – [Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels] admin | ||
---|---|---|---|
Line 31: | Line 31: | ||
The topic within which this work was carried out is related to the establishment of relationships between various methods of machine learning (ML). The ultimate goal of establishing such interrelations is to achieve a better theoretical understanding of these methods and their improvement. In particular, a correspondence has recently been established between the appropriate asymptotics of deep neural networks (DNNs), including convolutional ones (CNNs), and the ML method based on Gaussian processes. Since Gaussian processes are mathematically equivalent to free (Euclidean) quantum field theory (QFT), one of the intriguing consequences of these relationships is the potential for using a broad range of QFT methods for analyzing DNNs. There are evidences (including experimental) that non-asymptotic (that is, implementable in practice) DNNs correspond to QFT with interactions. An important feature of convolutional networks is their equivariance (consistency) with respect to the symmetry transformations of the input data. In this work, we establish a relationship between the many-channel limit of equivariant CNNs and the corresponding equivariant Gaussian process (GP), and hence the QFT with the appropriate symmetry. The approach used provides explicit equivariance at each stage of the derivation of the relationship. | The topic within which this work was carried out is related to the establishment of relationships between various methods of machine learning (ML). The ultimate goal of establishing such interrelations is to achieve a better theoretical understanding of these methods and their improvement. In particular, a correspondence has recently been established between the appropriate asymptotics of deep neural networks (DNNs), including convolutional ones (CNNs), and the ML method based on Gaussian processes. Since Gaussian processes are mathematically equivalent to free (Euclidean) quantum field theory (QFT), one of the intriguing consequences of these relationships is the potential for using a broad range of QFT methods for analyzing DNNs. There are evidences (including experimental) that non-asymptotic (that is, implementable in practice) DNNs correspond to QFT with interactions. An important feature of convolutional networks is their equivariance (consistency) with respect to the symmetry transformations of the input data. In this work, we establish a relationship between the many-channel limit of equivariant CNNs and the corresponding equivariant Gaussian process (GP), and hence the QFT with the appropriate symmetry. The approach used provides explicit equivariance at each stage of the derivation of the relationship. | ||
+ | |||
+ | ===== Modeling images of proton events for the TAIGA project using a generative adversarial network: features of the network architecture and the learning process ===== | ||
+ | |||
+ | **Ju.Dubenskaya**, | ||
+ | A.P.Kryukov, | ||
+ | |||
+ | //Short presentation (15 min)// | ||
+ | |||
+ | High-energy particles interacting with the Earth atmosphere give rise to extensive air showers emitting Cherenkov light. This light can be detected on the ground by imaging atmospheric Cherenkov telescopes (IACTs). One of the main problems solved during primary processing of experimental data is the separation of signal events (gamma-quanta) against the hadronic background, the bulk of which is made up of proton events. To ensure correct gamma event/ | ||
===== Use of conditional generative adversarial networks to improve representativity of data in optical spectroscopy ===== | ===== Use of conditional generative adversarial networks to improve representativity of data in optical spectroscopy ===== | ||
Line 120: | Line 129: | ||
Alexander Kryukov, | Alexander Kryukov, | ||
Evgeny Postnikov SINP MSU, Russia | Evgeny Postnikov SINP MSU, Russia | ||
+ | |||
+ | //Short presentation (15 min)// | ||
Extensive air showers created by high-energy particles interacting | Extensive air showers created by high-energy particles interacting |
dlcp21/abstracts.1624367657.txt.gz · Last modified: 22/06/2021 16:14 by admin