Pruning deep neural networks is a widely used strategy to alleviate the computational burden in machine learning.
Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions.
Cellular functions crucially depend on the precise execution of complex biochemical reactions taking place on the chromatin fiber in the tightly packed environment of the cell nucleus.
Despite significant efforts, both practical and theoretical, training deep learning models robust to adversarial attacks is still an open problem.
Biochemical reactions inside living cells often occur in the presence of crowders -- molecules that do not participate in the reactions but influence the reaction rates through excluded volume effects.
We empirically show that interpretations provided by Bayesian Neural Networks are considerably more stable under adversarial perturbations of the inputs and even under direct attacks to the explanations.
We propose two training techniques for improving the robustness of Neural Networks to adversarial attacks, i. e. manipulations of the inputs that are maliciously crafted to fool networks into incorrect predictions.
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications.
We construct here a general method based on spectral analysis of the transition matrix of the CTMC, without the need for a population structure.
The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets.
We consider the problem of computing first-passage time distributions for reaction processes modelled by master equations.
In summary, this review gives a self-contained introduction to modelling, approximations and inference methods for stochastic chemical kinetics.
Dynamical systems with large state-spaces are often expensive to thoroughly explore experimentally.
Biological systems are often modelled at different levels of abstraction depending on the particular aims/resources of a study.
Using these higher order features across promoter-proximal regions, we are able to construct a powerful machine learning predictor of gene expression, significantly improving upon the predictive power of average DNA methylation levels.
Genomics Quantitative Methods
Our work provides both insights into spatio-temporal stochastic systems, and a practical solution to a long-standing problem in computational modelling.
We consider the inverse problem of reconstructing the posterior measure over the trajec- tories of a diffusion process from discrete time observations and continuous time constraints.
We consider continuous time Markovian processes where populations of individual agents interact stochastically according to kinetic rules.
We present a novel approach to learn the formulae characterising the emergent behaviour of a dynamical system from system observations.
We propose an approximate inference algorithm for continuous time Gaussian-Markov process models with both discrete and continuous time likelihoods.
By discussing two examples, we show how to approximate the distribution of the robustness score and its key indicators: the average robustness and the conditional average robustness.
We present a hybrid model of a biological filter, a genetic circuit which removes fast fluctuations in the cell's internal representation of the extra cellular environment.
We consider the problem of joint modelling of metabolic signals and gene expression in systems biology applications.
Spatio-temporal point process models play a central role in the analysis of spatially distributed systems in several disciplines.
We consider the problem of Bayesian inference for continuous time multi-stable stochastic systems which can change both their diffusion and drift parameters at discrete times.
We present a novel approach to inference in conditionally Gaussian continuous time stochastic processes, where the latent process is a Markovian jump process.