DTU Studieprojekt - Improving deep learning for electron microscopy

Danmarks Tekniske Universitet (DTU)

Studieprojekt/speciale
Storkøbenhavn

Improving deep learning for electron microscopy

Udbyder
Vejleder
Sted
København og omegn
Deep learning is the application of neural networks with many layers to machine learning problems. We expect that deep learning can be a game-changer for analyzing data from Transmission Electron Microscopy (TEM). It can automatize the analysis of large amounts of data, eliminate the bias of the person analysing the images, provide quantitative and statistical data, and even help extracting information that is normally difficult to get from TEM.
In a collaboration between the CAMD theory group at DTU Physics and the electron microscopists at DTU CEN/Danchip we have developed a method for training deep convolutional neural networks on simulated TEM images and applying them on real experimental data [1]. We have made our prototype software publicly available [2].
Unlike most image analysis problems, we are in the beneficial and quite unusual situation of having access to almost free training data, since high-resolution TEM images can be simulated reliably from atomic structures, including realistic noise and imperfections in the microscope optics.
The neural network architecture is inspired by the networks generally used for automated image analysis and segmentation. However, the network architecture has almost not been optimized, nor has the training procedure. We expect that the performance can be significantly enhanced by addressing this.
This project has two aspects, a BSc project will focus one one of them while a MSc will focus on both.
* To improve the neural network by optimizing the network architecture and the training algorithm, and by incorporating recent ideas from the litterature on image analysis and image segmentation.
* To turn the current collection of scripts and software snippets into a package that can realistically be used by an electron microscopist with no prior experience in machine learning.experience with

Figure: The architecture of the neural network [1]. Information flows from left to right. The different-colored rectangles refer to the different architecture elements. Below the rectangles, the spatial and channel dimensions are given as height × width × number of channels (feature maps). The features are downsampled in an encoding path and upsampled through a decoding path in order to represent non-local information. Skip connections ensure that it is possible to retain the original spatial information. Although the size of the input images is shown as 256 × 256, this is not part of the network architecture, and the network can be used on images of any size.

References:
[1] J. Madsen et al.: A Deep Learning Approach to Identify Local Structures in Atomic-Resolution Transmission Electron Microscopy Images, Adv. Theory Simul. 1, 1800037 (2018). Preprint available at https://arxiv.org/abs/1802.03008
[2] https://gitlab.com/schiotz/NeuralNetwork_HRTEM
Forudsætninger
Prior knowledge of Python and neural networks. Some knowledge of solid state physics and/or electron microscopy is an advantage, but not required.

Emneord

Kontakt
Virksomhed/organisation
DTU Fysik

Navn
Jakob Schiøtz

Stilling
Professor

Mail
schiotz@fysik.dtu.dk

Vejleder-info
Bachelor i Kunstig Intelligens og Data
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Bachelor i General Engineering
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Bachelor i Geofysik og Rumteknologi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Bachelor i Matematik og Teknologi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Bachelor i Fysik og Nanoteknologi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Kandidatuddannelsen i Anvendt Kemi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Kandidatuddannelsen i Informationsteknologi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Kandidatuddannelsen i Geofysik og Rumteknologi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Kandidatuddannelsen i Elektroteknologi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Kandidatuddannelsen i Matematisk Modellering og Computing
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale

Kandidatuddannelsen i Fysik og Nanoteknologi
Vejleder
Jakob Schiøtz

Medvejledere
Thomas Willum Hansen

ECTS-point
15 - 35

Type
Bachelorprojekt, Kandidatspeciale


Login for at se hele opslaget

Dette jobopslag er kun tilgængeligt for vores brugere. Log ind eller opret en profil - det er gratis og tager kun to minutter.

Log ind med sociale medier


Log ind med din karriereprofil

@


Glemt kode Ny bruger

Løbende ansøgningsfrist

Angiv venligst i din ansøgning, at du har ansøgt opslaget via Studerende Online

Studieprojekt/speciale
Storkøbenhavn
Elektro & Telekommunikation
IT
Kemi, Biotek & Materialer
Klima, Miljø & Energi
Maskin & Design
Matematik, Fysik & Nano
Naturvidenskab
Teknik & Teknologi
Forskning & Udvikling
Naturvidenskab
Teknik



Danmarks Tekniske Universitet (DTU) - hurtigt overblik


Danmarks Tekniske Universitet (DTU)
Danmarks Tekniske Universitet (DTU)
DTU er et teknisk eliteuniversitet med international rækkevidde og standard. Vores mission er at udvikle og nyttiggøre naturvidenskab og teknisk videnskab til gavn for samfundet. 11.200 studerende uddanner sig her til fremtiden, og 6.000 medarbejdere har hver dag fokus på uddannelse, forskning, myndighedsrådgivning og innovation, som bidrager til øget vækst og velfærd.

Placering
Anker Engelunds Vej 1
2800 Kgs. Lyngby
Logo: Danmarks Tekniske Universitet (DTU)
Efterspørgsel efter nye talenter

Hvilke jobtyper og arbejdsområder udbyder vi normalt og hvor mange nye talenter søger vi efter?


Nyeste tweets
Henter tweets...
Facebook feed

Henter facebook feed...

LinkedIn

Følg vores aktiviteter på LinkedIn.


Webside

Få mere info omkring vores virksomhed på vores egne websider:

www.dtu.dk


Danmarks Tekniske Universitet (DTU) i Google

Er der andre informationer om os, som du burde vide? Se, hvad en Google-søgning siger.



https://studerendeonline.dk/job/1242907/
Vi bruger cookies til statistik, sociale medier og brugeroplevelse. Ved at bruge sitet accepterer du vores privatlivspolitik. (luk)
HPT