Bradley J. Nelson

Lek-Heng Lim, Bradley J. Nelson

We explain equivariant neural networks, a notion underlying breakthroughs in machine learning from deep convolutional neural networks for computer vision to AlphaFold 2 for protein structure prediction, without assuming knowledge of equivariance or neural networks. The basic mathematical ideas are simple but are often obscured by engineering complications that come with practical realizations. We extract and focus on the mathematical aspects, and limit ourselves to a cursory treatment of the engineering issues at the end.

Neelaksh Singh, Jasan Zughaibi, Denis von Arx et al.

Electromagnetic navigation systems (eMNS) are increasingly used in minimally invasive procedures such as endovascular interventions and targeted drug delivery due to their ability to generate fast and precise magnetic fields. In this paper, we utilize the OctoMag and a custom 13-coil eMNS to achieve remote levitation and control of multiple rigid bodies across large air gaps, showcasing the dynamic capabilities of such systems. A compact parametric analytical model maps coil currents to the forces and torques acting on the levitating object, eliminating the need for computationally expensive simulations or lookup tables and establishing a levitator- and platform-agnostic control framework. Translational motion is stabilized using linear quadratic regulators. A nonlinear time-invariant controller is used to regulate the reduced attitude accounting for the inherent uncontrollability of rotations about the dipole axis and stabilizing the full five degrees of freedom controllable pose subspace. We analyze key design limitations and evaluate the approach through trajectory tracking experiments across different objects and actuation platforms. Notably, our proposed controller demonstrates superiority over an equivalent baseline PID formulation, reliably tracking large spatial angles up to 65$^\circ$. This work demonstrates the dynamic capabilities and potential of feedback control in electromagnetic navigation, which is likely to open up new medical applications.

Alex. H. Barnett, Bradley J. Nelson, J. Matthew Mahoney

We apply boundary integral equations for the first time to the two-dimensional scattering of time-harmonic waves from a smooth obstacle embedded in a continuously-graded unbounded medium. In the case we solve the square of the wavenumber (refractive index) varies linearly in one coordinate, i.e. $(Δ+ E + x_2)u(x_1,x_2) = 0$ where $E$ is a constant; this models quantum particles of fixed energy in a uniform gravitational field, and has broader applications to stratified media in acoustics, optics and seismology. We evaluate the fundamental solution efficiently with exponential accuracy via numerical saddle-point integration, using the truncated trapezoid rule with typically 100 nodes, with an effort that is independent of the frequency parameter $E$. By combining with high-order Nystrom quadrature, we are able to solve the scattering from obstacles 50 wavelengths across to 11 digits of accuracy in under a minute on a desktop or laptop.

Rickard Brüel-Gabrielsson, Bradley J. Nelson, Anjan Dwaraknath et al.

Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning. We present a differentiable topology layer that computes persistent homology based on level set filtrations and edge-based filtrations. We present three novel applications: the topological layer can (i) regularize data reconstruction or the weights of machine learning models, (ii) construct a loss on the output of a deep generative network to incorporate topological priors, and (iii) perform topological adversarial attacks on deep networks trained with persistence features. The code (www.github.com/bruel-gabrielsson/TopologyLayer) is publicly available and we hope its availability will facilitate the use of persistent homology in deep learning and other gradient based applications.

Bradley J. Nelson, Yuan Luo

Dimensionality reduction techniques are powerful tools for data preprocessing and visualization which typically come with few guarantees concerning the topological correctness of an embedding. The interleaving distance between the persistent homology of Vietoris-Rips filtrations can be used to identify a scale at which topological features such as clusters or holes in an embedding and original data set are in correspondence. We show how optimization seeking to minimize the interleaving distance can be incorporated into dimensionality reduction algorithms, and explicitly demonstrate its use in finding an optimal linear projection. We demonstrate the utility of this framework to data visualization.

Deqing Fu, Bradley J. Nelson

Dense prediction tasks such as depth perception and semantic segmentation are important applications in computer vision that have a concrete topological description in terms of partitioning an image into connected components or estimating a function with a small number of local extrema corresponding to objects in the image. We develop a form of topological regularization based on persistent homology that can be used in dense prediction tasks with these topological descriptions. Experimental results show that the output topology can also appear in the internal activations of trained neural networks which allows for a novel use of topological regularization to the internal states of neural networks during training, reducing the computational cost of the regularization. We demonstrate that this topological regularization of internal activations leads to improved convergence and test benchmarks on several problems and architectures.

Francois Drielsma, Qing Lin, Pierre Côte de Soux et al.

Liquid Argon Time Projection Chambers (LArTPCs) are a class of detectors that produce high resolution images of charged particles within their sensitive volume. In these images, the clustering of distinct particles into superstructures is of central importance to the current and future neutrino physics program. Electromagnetic (EM) activity typically exhibits spatially detached fragments of varying morphology and orientation that are challenging to efficiently assemble using traditional algorithms. Similarly, particles that are spatially removed from each other in the detector may originate from a common interaction. Graph Neural Networks (GNNs) were developed in recent years to find correlations between objects embedded in an arbitrary space. The Graph Particle Aggregator (GrapPA) first leverages GNNs to predict the adjacency matrix of EM shower fragments and to identify the origin of showers, i.e. primary fragments. On the PILArNet public LArTPC simulation dataset, the algorithm achieves achieves a shower clustering accuracy characterized by a mean adjusted Rand index (ARI) of 97.8 % and a primary identification accuracy of 99.8 %. It yields a relative shower energy resolution of $(4.1+1.4/\sqrt{E (\text{GeV})})\,\%$ and a shower direction resolution of $(2.1/\sqrt{E(\text{GeV})})^{\circ}$. The optimized algorithm is then applied to the related task of clustering particle instances into interactions and yields a mean ARI of 99.2 % for an interaction density of $\sim\mathcal{O}(1)\,m^{-3}$.

Ruoxi Yu, Samuel L. Charreyron, Quentin Boehler et al.

Electromagnetic Navigation Systems (eMNS) can be used to control a variety of multiscale devices within the human body for remote surgery. Accurate modeling of the magnetic fields generated by the electromagnets of an eMNS is crucial for the precise control of these devices. Existing methods assume a linear behavior of these systems, leading to significant modeling errors within nonlinear regions exhibited at higher magnetic fields. In this paper, we use a random forest (RF) and an artificial neural network (ANN) to model the nonlinear behavior of the magnetic fields generated by an eMNS. Both machine learning methods outperformed the state-of-the-art linear multipole electromagnet method (LMEM). The RF and the ANN model reduced the root mean squared error of the LMEM when predicting the field magnitude by around 40% and 80%, respectively, over the entire current range of the eMNS. At high current regions, especially between 30 and 35 A, the field-magnitude RMSE improvement of the ANN model over the LMEM was over 35 mT. This study demonstrates the feasibility of using machine learning methods to model an eMNS for medical applications, and its ability to account for complex nonlinear behavior at high currents. The use of machine learning thus shows promise for improving surgical procedures that use magnetic navigation.