Causal Navigation by Continuous-time Neural Networks

Vorbach, Charles; Hasani, Ramin; Amini, Alexander; Lechner, Mathias; Rus, Daniela

doi:10.48550/arxiv.2106.08314

Cited by 6 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is caused especially by the high structural complexity leaving many structural details unresolved or concealed, which causes a high uncertainty of the manual annotations. Unsupervised and self-supervised machine learning procedures such as spatiotemporal vision transformers 58 or liquid neural networks 59 are promising tools to trace and identify individual cells in heavily cluttered images of BNNs.…”

Section: Discussionmentioning

confidence: 99%

Towards a comprehensive approach for characterizing cell activity in low contrast microscopic images

Baar

Kuragano

Tokuraku

et al. 2022

Preprint

View full text Add to dashboard Cite

When studying physical cellular response observed by light microscopy, variations in cell behavior are difficult to quantitatively measure and are often only discussed on a subjective level. Hence, cell properties are described qualitatively based on a researcher’s impressions. In this study, we aim to define a comprehensive approach to estimate the physical cell activity based on migration and morphology based on statistical analysis of a cell population within a predefined field of view and timespan. We present quantitative measurements of the influence of drugs such as cytochalasin D and taxol on human neuroblastoma, SH-SY5Y cell populations. Both chemicals are well known to interact with the cytoskeleton and affect the cell morphology and motility. Being able to compute the physical properties of each cell for a given observation time, requires precise localization of each cell even when in an adhesive state. Also, the risk of confusion through contaminants is desired to be minimized. In relation to the cell detection process, we have developed a customized encoder-decoder based deep learning cell detection and tracking procedure. Further, we discuss the accuracy of our approach to quantify cell activity and its viability in regard to the cell detection accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Towards a comprehensive approach for characterizing cell activity in low contrast microscopic images

Baar

Kuragano

Tokuraku

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To avoid this, for tasks that require long-term dependencies, it is better to use them together with mixed memory networks (See CfC-mmRNN). Moreover, we speculate that inferring causality from ODE-based networks might be more straightforward than a closed-form solution (Vorbach et al, 2021). It would also be beneficial to assess if verifying a continuous neural flow (Grunbacher et al, 2021) is more tractable by an ODE representation of the system or their closed form.…”

Section: Scope Discussion and Conclusionmentioning

confidence: 99%

Closed-form Continuous-time Neural Models

Hasani¹,

Lechner²,

Amini³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Continuous-depth neural models, where the derivative of the model's hidden state is defined by a neural network, have enabled strong sequential data processing capabilities. However, these models rely on advanced numerical differential equation (DE) solvers resulting in a significant overhead both in terms of computational cost and model complexity. In this paper, we present a new family of models, termed Closed-form Continuous-depth (CfC) networks, that are simple to describe and at least one order of magnitude faster while exhibiting equally strong modeling abilities compared to their ODE-based counterparts. The models are hereby derived from the analytical closed-form solution of an expressive subset of time-continuous models, thus alleviating the need for complex DE solvers all together. In our experimental evaluations, we demonstrate that CfC networks outperform advanced, recurrent models over a diverse set of time-series prediction tasks, including those with long-term dependencies and irregularly sampled data. We believe our findings open new opportunities to train and deploy rich, continuous neural models in resource-constrained settings, which demand both performance and efficiency.

show abstract

“…A potential future avenue of research emerging from this work will be to simultaneously learn the system dynamics and unsafe sets with BarrierNets. This can be enabled using the expressive class of continuous-time neural network models (Chen et al, 2018;Lechner et al, 2020a;Hasani et al, 2021b;Vorbach et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

BarrierNet: A Safety-Guaranteed Layer for Neural Networks

Xiao¹,

Hasani²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper introduces differentiable higher-order control barrier functions (CBF) that are end-toend trainable together with learning systems. CBFs are usually overly conservative, while guaranteeing safety. Here, we address their conservativeness by softening their definitions using environmental dependencies without loosing safety guarantees, and embed them into differentiable quadratic programs. These novel safety layers, termed a BarrierNet, can be used in conjunction with any neural network-based controller, and can be trained by gradient descent. BarrierNet allows the safety constraints of a neural controller be adaptable to changing environments. We evaluate them on a series of control problems such as traffic merging and robot navigations in 2D and 3D space, and demonstrate their effectiveness compared to state-of-the-art approaches.

show abstract

Causal Navigation by Continuous-time Neural Networks

Cited by 6 publications

References 27 publications

Towards a comprehensive approach for characterizing cell activity in low contrast microscopic images

Towards a comprehensive approach for characterizing cell activity in low contrast microscopic images

Closed-form Continuous-time Neural Models

BarrierNet: A Safety-Guaranteed Layer for Neural Networks

Contact Info

Product

Resources

About