Pre-conference workshops on Tuesday, January 8th:

Maximum capacity per workshop is limited to 150 people. First registrants will be considered with highest priority. No lunch has been organized for workshop participants. Please enjoy the crêperies and restaurants of downtown Rennes.

Adaptive optics for microscopy

The course will review the practice and implementation of adaptive optics in microscope systems. This will be relevant to researchers who are interested in using adaptive optics in custom built microscopes of various modalities.

Instructors: Martin Booth and colleagues (University of Oxford, Oxford, UK).

Machine and deep learning in bioimage analysis and microscopy: Tutorial introduction for microscopists

The goal of the workshop is to provide overview talks  and lectures for practitioners and theoreticians and to discuss the range of applications of deep learning in bioimaging, as well as the new challenges in microscopy raised by the need to better understand and analyze living systems at different scales.  Another objective is to present the potential and practical and theoretical limitations of deep architectures for large scale machine learning applied to quantitative bioimaging.

Instructors: Seth Flaxman (Imperial College, London, UK); Julien Mairal (INRIA, Grenoble, France); Christophe Zimmer (Institut Pasteur, Paris, France).

3D Single molecule microscopy data analysis

Instructor: Daniel Sage (EPFL, Lausanne, Switzerland); Jonas Ries (EMBL; Heidelberg, Germany); Benoit Lelandais (Institut Pasteur, Pairs, France); Anish Abraham (Texas A&M University Health Science Center, College Station, US)

Adaptive optics for microscopy

08:30 – 10:45 Practicle Aspects of Adaptive Optics for Microscopes (Martin Booth, University of Oxford)

Machine and deep learning in bioimage analysis and microscopy: Tutorial introduction for microscopists

11:00 – 12:30 What is machine learning? (Seth Flaxman, Imperial College)

• Supervised vs unsupervised learning: k-nearest neighbors, k-means clustering
• From linear to nonlinear methods: transformations, feature engineering, and the kernel trick
• Bias vs variance, and how to deal with the problem of overfitting.
• Regularization, lasso, ridge regression, and the elasticnet

12:30 – 13:30 Lunch

13:30 – 14:30 Advanced machine learning (Seth Flaxman, Imperial College)

• Ensemble methods
• Gaussian processes

14:30 – 15:45 Optimization (Julien Mairal, INRIA)

In this lecture, we will discuss a few techniques recently introduced in machine learning and optimization to deal with large amounts of data. We will focus on regularized empirical risk minimization problems, which consists of minimizing a large sum of functions, and cover also stochastic optimization techniques for minimizing expectations. Concepts we are planning to cover include

• Stochastic gradient descent techniques with variance reduction
• Nesterov’s acceleration
• Quasi-Newton techniques.

We will also consider variants that allow dealing with nonsmooth regularization such as the l1-norm, which is useful for sparse estimation in high dimension.

15:45 – 16:45 Deep Learning (Christophe Zimmer, Institut Pasteur)

• what deep learning can do
  • image classification
  • other applications
• how deep learning works
  • forward propagation
  • convnets
  • training
  • babysitting neural nets

DIY deep learning with Keras

3D Single molecule microscopy data analysis

17:15 – 17:45 Introduction of techniques for 3D SMLM and software

• Analysis methods, performances, limitations, density
• Calibration (3D)
• Post-processing: Wobble correction, drift correction, temporal grouping, rendering
• Challenge, reference datasets, metrics

17:45 – 18:05 Presentation and demonstration of QuickPALM or ThunderSTORM (Daniel Sage, EPFL)

18:05 – 18:25 Presentation and demonstration of SMAP (Jonas Ries, EMBL)

18:25 – 18:45 Presentation and demonstration of ZOLA-3D (Benoit Lelandais, Institut Pasteur)

18:45 – 19:05 Presentation and demonstration of MIAtool (Anish Abraham, TAMHSC)

19:05 – 19:15 Round-table