Search

Natural language allows robot programming to be accessible to everyone. However, the inherent fuzziness in natural language poses challenges for inflexible, traditional robot systems. We focus on instructions with fuzzy time requirements (e.g., "start in a few minutes"). Building on previous robotics research, we introduce fuzzy skills. These define an execution by the robot with so-called satisfaction functions representing vague execution time requirements. Such functions express a user's satisfaction over potential starting times for skill execution. When the robot handles multiple fuzzy skills, the satisfaction function provides a temporal tolerance window for execution, thus, enabling optimal scheduling based on satisfaction. We generalized such functions based on individual user expectations with a user study. The participants rated their satisfaction with an instruction's execution at various times. Our investigations reveal that trapezoidal functions best approximate the users' satisfaction. Additionally, the results suggest that users are more lenient if the execution is specified further into the future., Comment: 9 pages, 8 figures, to be published in 2024 IEEE International Conference on Robotic Computing (IRC)

A novel framework for hierarchical forecast updating is presented, addressing a critical gap in the forecasting literature. By assuming a temporal hierarchy structure, the innovative approach extends hierarchical forecast reconciliation to effectively manage the challenge posed by partially observed data. This crucial extension allows, in conjunction with real-time data, to obtain updated and coherent forecasts across the entire temporal hierarchy, thereby enhancing decision-making accuracy. The framework involves updating base models in response to new data, which produces revised base forecasts. A subsequent pruning step integrates the newly available data, allowing for the application of any forecast reconciliation method to obtain fully updated reconciled forecasts. Additionally, the framework not only ensures coherence among forecasts but also improves overall accuracy throughout the hierarchy. Its inherent flexibility and interpretability enable users to perform hierarchical forecast updating concisely. The methodology is extensively demonstrated in a simulation study with various settings and comparing different data-generating processes, hierarchies, and reconciliation methods. Practical applicability is illustrated through two case studies in the energy sector, energy generation and solar power data, where the framework yields superior results compared to base models that do not incorporate new data, leading to more precise decision-making outcomes.

Reinforcement learning algorithms for mean-field games offer a scalable framework for optimizing policies in large populations of interacting agents. Existing methods often depend on online interactions or access to system dynamics, limiting their practicality in real-world scenarios where such interactions are infeasible or difficult to model. In this paper, we present Offline Munchausen Mirror Descent (Off-MMD), a novel mean-field RL algorithm that approximates equilibrium policies in mean-field games using purely offline data. By leveraging iterative mirror descent and importance sampling techniques, Off-MMD estimates the mean-field distribution from static datasets without relying on simulation or environment dynamics. Additionally, we incorporate techniques from offline reinforcement learning to address common issues like Q-value overestimation, ensuring robust policy learning even with limited data coverage. Our algorithm scales to complex environments and demonstrates strong performance on benchmark tasks like crowd exploration or navigation, highlighting its applicability to real-world multi-agent systems where online experimentation is infeasible. We empirically demonstrate the robustness of Off-MMD to low-quality datasets and conduct experiments to investigate its sensitivity to hyperparameter choices., Comment: Submitted to AAMAS

IceCloudNet is a novel method based on machine learning able to predict high-quality vertically resolved cloud ice water contents (IWC) and ice crystal number concentrations (N$_\textrm{ice}$). The predictions come at the spatio-temporal coverage and resolution of geostationary satellite observations (SEVIRI) and the vertical resolution of active satellite retrievals (DARDAR). IceCloudNet consists of a ConvNeXt-based U-Net and a 3D PatchGAN discriminator model and is trained by predicting DARDAR profiles from co-located SEVIRI images. Despite the sparse availability of DARDAR data due to its narrow overpass, IceCloudNet is able to predict cloud occurrence, spatial structure, and microphysical properties with high precision. The model has been applied to ten years of SEVIRI data, producing a dataset of vertically resolved IWC and N$_\textrm{ice}$ of clouds containing ice with a 3 kmx3 kmx240 mx15 minute resolution in a spatial domain of 30{\deg}W to 30{\deg}E and 30{\deg}S to 30{\deg}N. The produced dataset increases the availability of vertical cloud profiles, for the period when DARDAR is available, by more than six orders of magnitude and moreover, IceCloudNet is able to produce vertical cloud profiles beyond the lifetime of the recently ended satellite missions underlying DARDAR., Comment: his paper was submitted to Artificial Intelligence for the Earth Systems

Detectors at future high energy colliders will face enormous technical challenges. Disentangling the unprecedented numbers of particles expected in each event will require highly granular silicon pixel detectors with billions of readout channels. With event rates as high as 40 MHz, these detectors will generate petabytes of data per second. To enable discovery within strict bandwidth and latency constraints, future trackers must be capable of fast, power efficient, and radiation hard data-reduction at the source. We are developing a radiation hard readout integrated circuit (ROIC) in 28nm CMOS with on-chip machine learning (ML) for future intelligent pixel detectors. We will show track parameter predictions using a neural network within a single layer of silicon and hardware tests on the first tape-outs produced with TSMC. Preliminary results indicate that reading out featurized clusters from particles above a modest momentum threshold could enable using pixel information at 40 MHz., Comment: Contribution to the 42nd International Conference on High Energy Physics (ICHEP)

Efficient and fast reconstruction of anatomical structures plays a crucial role in clinical practice. Minimizing retrieval and processing times not only potentially enhances swift response and decision-making in critical scenarios but also supports interactive surgical planning and navigation. Recent methods attempt to solve the medical shape reconstruction problem by utilizing implicit neural functions. However, their performance suffers in terms of generalization and computation time, a critical metric for real-time applications. To address these challenges, we propose to leverage meta-learning to improve the network parameters initialization, reducing inference time by an order of magnitude while maintaining high accuracy. We evaluate our approach on three public datasets covering different anatomical shapes and modalities, namely CT and MRI. Our experimental results show that our model can handle various input configurations, such as sparse slices with different orientations and spacings. Additionally, we demonstrate that our method exhibits strong transferable capabilities in generalizing to shape domains unobserved at training time.

Conventional battery equivalent circuit models (ECMs) have limited capability to predict performance at high discharge rates, where lithium depleted regions may develop and cause a sudden exponential drop in the cell's terminal voltage. Having accurate predictions of performance under such conditions is necessary for electric vertical takeoff and landing (eVTOL) aircraft applications, where high discharge currents can be required during fault scenarios and the inability to provide these currents can be safety-critical. To address this challenge, we utilize data-driven modeling methods to derive a parsimonious addition to a conventional ECM that can capture the observed rapid voltage drop with only one additional state. We also provide a detailed method for identifying the resulting model parameters, including an extensive characterization data set along with a well-regularized objective function formulation. The model is validated against a novel data set of over 150 flights encompassing a wide array of conditions for an eVTOL aircraft using an application-specific and safety-relevant reserve duration metric for quantifying accuracy. The model is shown to predict the landing hover capability with an error mean and standard deviation of 2.9 and 6.2 seconds, respectively, defining the model's ability to capture the cell voltage behavior under high discharge currents.

In this paper, we present our first proposal of a machine learning system for the classification of freshwater snails of the genus Radomaniola. We elaborate on the specific challenges encountered during system design, and how we tackled them; namely a small, very imbalanced dataset with a high number of classes and high visual similarity between classes. We then show how we employed triplet networks and the multiple input modalities of images, measurements, and genetic information to overcome these challenges and reach a performance comparable to that of a trained domain expert., Comment: Spotlight at ICML 2024 AI for Science workshop

Forecast reconciliation has become a prominent topic in recent forecasting literature, with a primary distinction made between cross-sectional and temporal hierarchies. This work focuses on temporal hierarchies, such as aggregating monthly time series data to annual data. We explore the impact of various forecast reconciliation methods on temporally aggregated ARIMA models, thereby bridging the fields of hierarchical forecast reconciliation and temporal aggregation both theoretically and experimentally. Our paper is the first to theoretically examine the effects of temporal hierarchical forecast reconciliation, demonstrating that the optimal method aligns with a bottom-up aggregation approach. To assess the practical implications and performance of the reconciled forecasts, we conduct a series of simulation studies, confirming that the findings extend to more complex models. This result helps explain the strong performance of the bottom-up approach observed in many prior studies. Finally, we apply our methods to real data examples, where we observe similar results.

Silicon-based photonic biosensors, such as microring resonators and Mach-Zehnder interferometers, offer significant potential for the detection of analytes at low concentrations. To enhance response time and improve the limit of detection within practical time scales, dielectrophoresis (DEP) has been proposed as a viable solution. In this approach, two electrodes are placed in close proximity to the sensor surface. By applying an AC field, analytes are transported to the sensor surface due to the polarization of the solvent and the particles, effectively overcoming the diffusion barrier. In this communication, we explore various possibilities for realizing DEP electrodes for nanowire waveguides using commercially available photonic integrated circuit (PIC) technology. Finite Element Method (FEM) simulations suggest that the most beneficial electrode configuration is a planar electrode geometry on the device layer combined with a second electrode pair on the metal 1 layer.

We present a smart pixel prototype readout integrated circuit (ROIC) designed in CMOS 28 nm bulk process, with in-pixel implementation of an artificial intelligence (AI) / machine learning (ML) based data filtering algorithm designed as proof-of-principle for a Phase III upgrade at the Large Hadron Collider (LHC) pixel detector. The first version of the ROIC consists of two matrices of 256 smart pixels, each 25$\times$25 $\mu$m$^2$ in size. Each pixel consists of a charge-sensitive preamplifier with leakage current compensation and three auto-zero comparators for a 2-bit flash-type ADC. The frontend is capable of synchronously digitizing the sensor charge within 25 ns. Measurement results show an equivalent noise charge (ENC) of $\sim$30e$^-$ and a total dispersion of $\sim$100e$^-$ The second version of the ROIC uses a fully connected two-layer neural network (NN) to process information from a cluster of 256 pixels to determine if the pattern corresponds to highly desirable high-momentum particle tracks for selection and readout. The digital NN is embedded in-between analog signal processing regions of the 256 pixels without increasing the pixel size and is implemented as fully combinatorial digital logic to minimize power consumption and eliminate clock distribution, and is active only in the presence of an input signal. The total power consumption of the neural network is $\sim$ 300 $\mu$W. The NN performs momentum classification based on the generated cluster patterns and even with a modest momentum threshold, it is capable of 54.4\% - 75.4\% total data rejection, opening the possibility of using the pixel information at 40MHz for the trigger. The total power consumption of analog and digital functions per pixel is $\sim$ 6 $\mu$W per pixel, which corresponds to $\sim$ 1 W/cm$^2$ staying within the experimental constraints., Comment: IEEE NSS MIC RSTD 2024

Digital Twins have gained attention in various industries for simulation, monitoring, and decision-making, relying on ever-improving machine learning models. However, agricultural Digital Twin implementations are limited compared to other industries. Meanwhile, machine learning, particularly reinforcement learning, has shown potential in agricultural applications like optimizing decision-making, task automation, and resource management. A key aspect of Digital Twins is representing physical assets or systems in a virtual environment, which aligns well with reinforcement learning's need for environment representations to learn the best policy for a task. Reinforcement learning in agriculture can thus enable various Digital Twin applications in agricultural domains. This review aims to categorize existing research employing reinforcement learning in agricultural settings by application domains like robotics, greenhouse management, irrigation systems, and crop management, identifying potential future areas for reinforcement learning-based Digital Twins. It also categorizes the reinforcement learning techniques used, including tabular methods, Deep Q-Networks (DQN), Policy Gradient methods, and Actor-Critic algorithms, to overview currently employed models. The review seeks to provide insights into the state-of-the-art in integrating Digital Twins and reinforcement learning in agriculture, identifying gaps and opportunities for future research, and exploring synergies to tackle agricultural challenges and optimize farming, paving the way for more efficient and sustainable farming methodologies.

This white paper presents the current status of the R&D for Analysis Facilities (AFs) and attempts to summarize the views on the future direction of these facilities. These views have been collected through the High Energy Physics (HEP) Software Foundation's (HSF) Analysis Facilities forum, established in March 2022, the Analysis Ecosystems II workshop, that took place in May 2022, and the WLCG/HSF pre-CHEP workshop, that took place in May 2023. The paper attempts to cover all the aspects of an analysis facility.

This work addresses flexibility in deep learning by means of transductive reasoning. For adaptation to new data and tasks, e.g., in continual learning, existing methods typically involve tuning learnable parameters or complete re-training from scratch, rendering such approaches unflexible in practice. We argue that the notion of separating computation from memory by the means of transduction can act as a stepping stone for solving these issues. We therefore propose PARMESAN (parameter-free memory search and transduction), a scalable method which leverages a memory module for solving dense prediction tasks. At inference, hidden representations in memory are being searched to find corresponding patterns. In contrast to other methods that rely on continuous training of learnable parameters, PARMESAN learns via memory consolidation simply by modifying stored contents. Our method is compatible with commonly used architectures and canonically transfers to 1D, 2D, and 3D grid-based data. The capabilities of our approach are demonstrated at the complex task of continual learning. PARMESAN learns by 3-4 orders of magnitude faster than established baselines while being on par in terms of predictive performance, hardware-efficiency, and knowledge retention., Comment: preprint, 25 pages, 7 figures

We illustrate how purpose-specific, graphical modeling enables application experts with different levels of expertise to collaboratively design and then produce complex applications using their individual, purpose-specific modeling language. Our illustration includes seven graphical Integrated Modeling Environments (IMEs) that support full code generation, as well as four browser-based applications that were modeled and then fully automatically generated and produced using DIME, our most complex graphical IME. While the seven IMEs were chosen to illustrate the types of languages we support with our Language-Driven Engineering (LDE) approach, the four DIME products were chosen to give an impression of the power of our LDE-generated IMEs. In fact, Equinocs, Springer Nature's future editorial system for proceedings, is also being fully automatically generated and then deployed at their Dordrecht site using a deployment pipeline generated with Rig, one of the IMEs presented. Our technology is open source and the products presented are currently in use., Comment: 43 pages, 30 figures

In biotechnology Raman Spectroscopy is rapidly gaining popularity as a process analytical technology (PAT) that measures cell densities, substrate- and product concentrations. As it records vibrational modes of molecules it provides that information non-invasively in a single spectrum. Typically, partial least squares (PLS) is the model of choice to infer information about variables of interest from the spectra. However, biological processes are known for their complexity where convolutional neural networks (CNN) present a powerful alternative. They can handle non-Gaussian noise and account for beam misalignment, pixel malfunctions or the presence of additional substances. However, they require a lot of data during model training, and they pick up non-linear dependencies in the process variables. In this work, we exploit the additive nature of spectra in order to generate additional data points from a given dataset that have statistically independent labels so that a network trained on such data exhibits low correlations between the model predictions. We show that training a CNN on these generated data points improves the performance on datasets where the annotations do not bear the same correlation as the dataset that was used for model training. This data augmentation technique enables us to reuse spectra as training data for new contexts that exhibit different correlations. The additional data allows for building a better and more robust model. This is of interest in scenarios where large amounts of historical data are available but are currently not used for model training. We demonstrate the capabilities of the proposed method using synthetic spectra of Ralstonia eutropha batch cultivations to monitor substrate, biomass and polyhydroxyalkanoate (PHA) biopolymer concentrations during of the experiments.

Understanding the magnetoresistance (MR) of a magnetic material forms the basis for uncovering the orbital mechanisms and charge-spin interactions in the system. Although the parent state of iron-based high-temperature superconductors, including $BaFe_2As_2$, exhibits unusual electron transport properties resulting from spin and charge correlations, there is still valuable insight to be gained by understanding the in-plane MR effect due to twin domains in the orthorhombic antiferromagnetic (AF) ordered state. Here, we study the in-plane magnetoresistance anisotropy in detwinned $BaFe_2As_2$ and compare the results to the non-magnetic Ni-doped sample. We find that in the antiferromagnetically ordered state, $BaFe_2As_2$ exhibits anisotropic MR that becomes large at low temperatures and high fields. Both transverse and longitudinal MRs are highly anisotropic and dependent on the field and current orientations. These results cannot be fully explained by calculations considering only the anisotropic Fermi surface. Instead, the spin orientation of the ordered moment also affects the MR effect, suggesting the presence of a large charge-spin interaction in $BaFe_2As_2$ that is not present in the Ni-doped material.

We introduce liquid-resistance liquid-capacitance neural networks (LRCs), a neural-ODE model which considerably improve the generalization, accuracy, and biological plausibility of electrical equivalent circuits (EECs), liquid time-constant networks (LTCs), and saturated liquid time-constant networks (STCs), respectively. We also introduce LRC units (LRCUs), as a very efficient and accurate gated RNN-model, which results from solving LRCs with an explicit Euler scheme using just one unfolding. We empirically show and formally prove that the liquid capacitance of LRCs considerably dampens the oscillations of LTCs and STCs, while at the same time dramatically increasing accuracy even for cheap solvers. We experimentally demonstrate that LRCs are a highly competitive alternative to popular neural ODEs and gated RNNs in terms of accuracy, efficiency, and interpretability, on classic time-series benchmarks and a complex autonomous-driving lane-keeping task.

Quantitative measurement of crystals in high-resolution images allows for important insights into underlying material characteristics. Deep learning has shown great progress in vision-based automatic crystal size measurement, but current instance segmentation methods reach their limits with images that have large variation in crystal size or hard to detect crystal boundaries. Even small image segmentation errors, such as incorrectly fused or separated segments, can significantly lower the accuracy of the measured results. Instead of improving the existing pixel-wise boundary segmentation methods, we propose to use an instance-based segmentation method, which gives more robust segmentation results to improve measurement accuracy. Our novel method enhances flow maps with a size-aware multi-scale attention module. The attention module adaptively fuses information from multiple scales and focuses on the most relevant scale for each segmented image area. We demonstrate that our proposed attention fusion strategy outperforms state-of-the-art instance and boundary segmentation methods, as well as simple average fusion of multi-scale predictions. We evaluate our method on a refractory raw material dataset of high-resolution images with large variation in crystal size and show that our model can be used to calculate the crystal size more accurately than existing methods., Comment: has been accepted for publication in IEEE Transactions on Instrumentation and Measurement

Modern tourism in the 21st century is facing numerous challenges. Among these the rapidly growing number of tourists visiting space-limited regions like historical cities, museums and bottlenecks such as bridges is one of the biggest. In this context, a proper and accurate prediction of tourism volume and tourism flow within a certain area is important and critical for visitor management tasks such as sustainable treatment of the environment and prevention of overcrowding. Static flow control methods like conventional low-level controllers or limiting access to overcrowded venues could not solve the problem yet. In this paper, we empirically evaluate the performance of state-of-the-art deep-learning methods such as RNNs, GNNs, and Transformers as well as the classic statistical ARIMA method. Granular limited data supplied by a tourism region is extended by exogenous data such as geolocation trajectories of individual tourists, weather and holidays. In the field of visitor flow prediction with sparse data, we are thereby capable of increasing the accuracy of our predictions, incorporating modern input feature handling as well as mapping geolocation data on top of discrete POI data., Comment: Accepted for publication at the proceedings of the 5th International Data Science Conference - iDSC2023. arXiv admin note: substantial text overlap with arXiv:2206.13274

The combinatorics of track seeding has long been a computational bottleneck for triggering and offline computing in High Energy Physics (HEP), and remains so for the HL-LHC. Next-generation pixel sensors will be sufficiently fine-grained to determine angular information of the charged particle passing through from pixel-cluster properties. This detector technology immediately improves the situation for offline tracking, but any major improvements in physics reach are unrealized since they are dominated by lowest-level hardware trigger acceptance. We will demonstrate track angle and hit position prediction, including errors, using a mixture density network within a single layer of silicon as well as the progress towards and status of implementing the neural network in hardware on both FPGAs and ASICs., Comment: 6 pages, 3 figures, submitted to Neural Information Processing Systems 2023 (NeurIPS)

Mechanistic growth models play a major role in bioprocess engineering, design, and control. Their reasonable predictive power and their high level of interpretability make them an essential tool for computer aided engineering methods. Additionally, since they contain knowledge about cell physiology, the parameter estimates provide meaningful insights into the metabolism of the microorganism under study. However, the assumption of time invariance of the model parameters is often violated in real experiments, limiting their capacity to fully explain the observed dynamics. In this work, we propose a framework for identifying such violations and producing insights into misspecified mechanisms. The framework achieves this by allowing kinetic and process parameters to vary in time. We demonstrate the framework's capabilities by fitting a hybrid model based on a simple mechanistic growth model for E. coli with data generated in-silico by a much more complex one and identifying missing kinetics.

Inferring parameters of macro-kinetic growth models, typically represented by Ordinary Differential Equations (ODE), from the experimental data is a crucial step in bioprocess engineering. Conventionally, estimates of the parameters are obtained by fitting the mechanistic model to observations. Fitting, however, requires a significant computational power. Specifically, during the development of new bioprocesses that use previously unknown organisms or strains, efficient, robust, and computationally cheap methods for parameter estimation are of great value. In this work, we propose using Deep Neural Networks (NN) for directly predicting parameters of mechanistic models given observations. The approach requires spending computational resources for training a NN, nonetheless, once trained, such a network can provide parameter estimates orders of magnitude faster than conventional methods. We consider a training procedure that combines Neural Networks and mechanistic models. We demonstrate the performance of the proposed algorithms on data sampled from several mechanistic models used in bioengineering describing a typical industrial batch process and compare the proposed method, a typical gradient-based fitting procedure, and the combination of the two. We find that, while Neural Network estimates are slightly improved by further fitting, these estimates are measurably better than the fitting procedure alone., Comment: 7 pages, 3 figures

Cultivation experiments often produce sparse and irregular time series. Classical approaches based on mechanistic models, like Maximum Likelihood fitting or Monte-Carlo Markov chain sampling, can easily account for sparsity and time-grid irregularities, but most statistical and Machine Learning tools are not designed for handling sparse data out-of-the-box. Among popular approaches there are various schemes for filling missing values (imputation) and interpolation into a regular grid (alignment). However, such methods transfer the biases of the interpolation or imputation models to the target model. We show that Deep Set Neural Networks equipped with triplet encoding of the input data can successfully handle bio-process data without any need for imputation or alignment procedures. The method is agnostic to the particular nature of the time series and can be adapted for any task, for example, online monitoring, predictive control, design of experiments, etc. In this work, we focus on forecasting. We argue that such an approach is especially suitable for typical cultivation processes, demonstrate the performance of the method on several forecasting tasks using data generated from macrokinetic growth models under realistic conditions, and compare the method to a conventional fitting procedure and methods based on imputation and alignment., Comment: 9 pages, 3 figures

Bioprocesses are often characterized by nonlinear and uncertain dynamics. This poses particular challenges in the context of model predictive control (MPC). Several approaches have been proposed to solve this problem, such as robust or stochastic MPC, but they can be computationally expensive when the system is nonlinear. Recent advances in optimal control theory have shown that concepts from convex optimization, tube-based MPC, and difference of convex functions (DC) enable stable and robust online process control. The approach is based on systematic DC decompositions of the dynamics and successive linearizations around feasible trajectories. By convexity, the linearization errors can be bounded tightly and treated as bounded disturbances in a robust tube-based MPC framework. However, finding the DC composition can be a difficult task. To overcome this problem, we used a neural network with special convex structure to learn the dynamics in DC form and express the uncertainty sets using simplices to maximize the product formation rate of a cultivation with uncertain substrate concentration in the feed. The results show that this is a promising approach for computationally tractable data-driven robust MPC of bioprocesses., Comment: Corrected typos in equation

Clouds containing ice particles play a crucial role in the climate system. Yet they remain a source of great uncertainty in climate models and future climate projections. In this work, we create a new observational constraint of regime-dependent ice microphysical properties at the spatio-temporal coverage of geostationary satellite instruments and the quality of active satellite retrievals. We achieve this by training a convolutional neural network on three years of SEVIRI and DARDAR data sets. This work will enable novel research to improve ice cloud process understanding and hence, reduce uncertainties in a changing climate and help assess geoengineering methods for cirrus clouds., Comment: A Preprint. Submitted to Tackling Climate Change with Machine Learning: workshop at NeurIPS 2023

Highly granular pixel detectors allow for increasingly precise measurements of charged particle tracks. Next-generation detectors require that pixel sizes will be further reduced, leading to unprecedented data rates exceeding those foreseen at the High Luminosity Large Hadron Collider. Signal processing that handles data incoming at a rate of O(40MHz) and intelligently reduces the data within the pixelated region of the detector at rate will enhance physics performance at high luminosity and enable physics analyses that are not currently possible. Using the shape of charge clusters deposited in an array of small pixels, the physical properties of the traversing particle can be extracted with locally customized neural networks. In this first demonstration, we present a neural network that can be embedded into the on-sensor readout and filter out hits from low momentum tracks, reducing the detector's data volume by 54.4-75.4%. The network is designed and simulated as a custom readout integrated circuit with 28 nm CMOS technology and is expected to operate at less than 300 $\mu W$ with an area of less than 0.2 mm$^2$. The temporal development of charge clusters is investigated to demonstrate possible future performance gains, and there is also a discussion of future algorithmic and technological improvements that could enhance efficiency, data reduction, and power per area.