arXiv subjects

Ashwin De Silva

Publications and source records attributed to Ashwin De Silva.

12 recordsLinked to original sources

arXiv2026

Optimal control of the future via prospective learning with control

Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (RL). RL is mathematically distinct from supervised learning, which has been the main workhorse for the recent achievements in AI. Moreover, RL typically operates in a stationary environment with episodic resets, limiting its utility. Here, we extend supervised learning to address learning to control in non-stationary, reset-free environments. Using this framework, called ''Prospective Learning with Control'' (PLuC), we prove that under certain fairly general assumptions, empirical risk minimization (ERM) asymptotically achieves the Bayes optimal policy. We then consider a specific instance of prospective learning with control: foraging, a canonical task relevant to both natural and artificial agents. We illustrate that modern RL algorithms, which assume stationarity, struggle in these non-stationary reset-free environments. Even with time-aware modifications, they converge orders of magnitude slower than our prospective foraging agents on a simple 1-D foraging benchmark. Code is available at: https://github.com/neurodata/procontrol.

stat.ML↗

arXiv2025

Prospective Learning in Retrospect

In most real-world applications of artificial intelligence, the distributions of the data and the goals of the learners tend to change over time. The Probably Approximately Correct (PAC) learning framework, which underpins most machine learning algorithms, fails to account for dynamic data distributions and evolving objectives, often resulting in suboptimal performance. Prospective learning is a recently introduced mathematical framework that overcomes some of these limitations. We build on this framework to present preliminary results that improve the algorithm and numerical results, and extend prospective learning to sequential decision-making scenarios, specifically foraging. Code is available at: https://github.com/neurodata/prolearn2.

cs.LG↗

arXiv2025

Simple Calibration via Geodesic Kernels

Deep discriminative approaches, such as decision forests and deep neural networks, have recently found applications in many important real-world scenarios. However, deploying these learning algorithms in safety-critical applications raises concerns, particularly when it comes to ensuring calibration for both in-distribution and out-of-distribution regions. Many popular methods for in-distribution (ID) calibration, such as isotonic and Platt's sigmoidal regression, exhibit adequate ID calibration performance. However, these methods are not calibrated for the entire feature space, leading to overconfidence in the out-of-distribution (OOD) region. Existing OOD calibration methods generally exhibit poor ID calibration. In this paper, we jointly address the ID and OOD problems. We leveraged the fact that deep models learn to partition feature space into a union of polytopes, that is, flat-sided geometric objects. We introduce a geodesic distance to measure the distance between these polytopes and further distinguish samples within the same polytope using a Gaussian kernel. Our experiments on both tabular and vision benchmarks show that the proposed approaches, namely Kernel Density Forest (KDF) and Kernel Density Network (KDN), obtain well-calibrated posteriors for both ID and OOD samples, while mostly preserving the classification accuracy and extrapolating beyond the training data to handle OOD inputs appropriately.

cs.LG↗

arXiv2025

Prospective Learning: Learning for a Dynamic Future

In real-world applications, the distribution of the data, and our goals, evolve over time. The prevailing theoretical framework for studying machine learning, namely probably approximately correct (PAC) learning, largely ignores time. As a consequence, existing strategies to address the dynamic nature of data and goals exhibit poor real-world performance. This paper develops a theoretical framework called "Prospective Learning" that is tailored for situations when the optimal hypothesis changes over time. In PAC learning, empirical risk minimization (ERM) is known to be consistent. We develop a learner called Prospective ERM, which returns a sequence of predictors that make predictions on future data. We prove that the risk of prospective ERM converges to the Bayes risk under certain assumptions on the stochastic process generating the data. Prospective ERM, roughly speaking, incorporates time as an input in addition to the data. We show that standard ERM as done in PAC learning, without incorporating time, can result in failure to learn when distributions are dynamic. Numerical experiments illustrate that prospective ERM can learn synthetic and visual recognition problems constructed from MNIST and CIFAR-10. Code at https://github.com/neurodata/prolearn.

stat.ML↗

arXiv2024

Approximately optimal domain adaptation with Fisher's Linear Discriminant

We propose a class of models based on Fisher's Linear Discriminant (FLD) in the context of domain adaptation. The class is the convex combination of two hypotheses: i) an average hypothesis representing previously seen source tasks and ii) a hypothesis trained on a new target task. For a particular generative setting we derive the optimal convex combination of the two models under 0-1 loss, propose a computable approximation, and study the effect of various parameter settings on the relative risks between the optimal hypothesis, hypothesis i), and hypothesis ii). We demonstrate the effectiveness of the proposed optimal classifier in the context of EEG- and ECG-based classification settings and argue that the optimal classifier can be computed without access to direct information from any of the individual source tasks. We conclude by discussing further applications, limitations, and possible future directions.

eess.SP↗

arXiv2023

Prospective Learning: Principled Extrapolation to the Future

Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in distribution or change adversarially. But these assumptions can be either too optimistic or pessimistic for many problems in the real world. Real world scenarios evolve over multiple spatiotemporal scales with partially predictable dynamics. Here we reformulate the learning problem to one that centers around this idea of dynamic futures that are partially learnable. We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning. We argue that prospective learning more accurately characterizes many real world problems that (1) currently stymie existing artificial intelligence solutions and/or (2) lack adequate explanations for how natural intelligences solve them. Thus, studying prospective learning will lead to deeper insights and solutions to currently vexing challenges in both natural and artificial intelligences.

cs.LG↗

arXiv2023

The Value of Out-of-Distribution Data

We expect the generalization error to improve with more samples from a similar task, and to deteriorate with more samples from an out-of-distribution (OOD) task. In this work, we show a counter-intuitive phenomenon: the generalization error of a task can be a non-monotonic function of the number of OOD samples. As the number of OOD samples increases, the generalization error on the target task improves before deteriorating beyond a threshold. In other words, there is value in training on small amounts of OOD data. We use Fisher's Linear Discriminant on synthetic datasets and deep networks on computer vision benchmarks such as MNIST, CIFAR-10, CINIC-10, PACS and DomainNet to demonstrate and analyze this phenomenon. In the idealistic setting where we know which samples are OOD, we show that these non-monotonic trends can be exploited using an appropriately weighted objective of the target and OOD empirical risk. While its practical utility is limited, this does suggest that if we can detect OOD samples, then there may be ways to benefit from them. When we do not know which samples are OOD, we show how a number of go-to strategies such as data-augmentation, hyper-parameter optimization, and pre-training are not enough to ensure that the target generalization error does not deteriorate with the number of OOD samples in the dataset.

cs.LG↗

arXiv2021

Towards Accurate Cross-Domain In-Bed Human Pose Estimation

Human behavioral monitoring during sleep is essential for various medical applications. Majority of the contactless human pose estimation algorithms are based on RGB modality, causing ineffectiveness in in-bed pose estimation due to occlusions by blankets and varying illumination conditions. Long-wavelength infrared (LWIR) modality based pose estimation algorithms overcome the aforementioned challenges; however, ground truth pose generations by a human annotator under such conditions are not feasible. A feasible solution to address this issue is to transfer the knowledge learned from images with pose labels and no occlusions, and adapt it towards real world conditions (occlusions due to blankets). In this paper, we propose a novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images in real world conditions. Our experiments and analysis show the effectiveness of our approach over multiple standard human pose estimation baselines.

cs.CV↗

arXiv2021

A Thickness Sensitive Vessel Extraction Framework for Retinal and Conjunctival Vascular Tortuosity Analysis

Systemic diseases such as diabetes, hypertension, atherosclerosis are among the leading causes of annual human mortality rate. It is suggested that retinal and conjunctival vascular tortuosity is a potential biomarker for such systemic diseases. Most importantly, it is observed that the tortuosity depends on the thickness of these vessels. Therefore, selective calculation of tortuosity within specific vessel thicknesses is required depending on the disease being analysed. In this paper, we propose a thickness sensitive vessel extraction framework that is primarily applicable for studies related to retinal and conjunctival vascular tortuosity. The framework uses a Convolutional Neural Network based on the IterNet architecture to obtain probability maps of the entire vasculature. They are then processed by a multi-scale vessel enhancement technique that exploits both fine and coarse structural vascular details of these probability maps in order to extract vessels of specified thicknesses. We evaluated the proposed framework on four datasets including DRIVE and SBVPI, and obtained Matthew's Correlation Coefficient values greater than 0.71 for all the datasets. In addition, the proposed framework was utilized to determine the association of diabetes with retinal and conjunctival vascular tortuosity. We observed that retinal vascular tortuosity (Eccentricity based Tortuosity Index) of the diabetic group was significantly higher (p < .05) than that of the non-diabetic group and that conjunctival vascular tortuosity (Total Curvature normalized by Arc Length) of diabetic group was significantly lower (p < .05) than that of the non-diabetic group. These observations were in agreement with the literature, strengthening the suitability of the proposed framework.

eess.IV↗

arXiv2020

A Joint Convolutional and Spatial Quad-Directional LSTM Network for Phase Unwrapping

Phase unwrapping is a classical ill-posed problem which aims to recover the true phase from wrapped phase. In this paper, we introduce a novel Convolutional Neural Network (CNN) that incorporates a Spatial Quad-Directional Long Short Term Memory (SQD-LSTM) for phase unwrapping, by formulating it as a regression problem. Incorporating SQD-LSTM can circumvent the typical CNNs' inherent difficulty of learning global spatial dependencies which are vital when recovering the true phase. Furthermore, we employ a problem specific composite loss function to train this network. The proposed network is found to be performing better than the existing methods under severe noise conditions (Normalized Root Mean Square Error of 1.3 % at SNR = 0 dB) while spending a significantly less computational time (0.054 s). The network also does not require a large scale dataset during training, thus making it ideal for applications with limited data that require fast and accurate phase unwrapping.

cs.LG↗

arXiv2020

Low-cost Active Dry-Contact Surface EMG Sensor for Bionic Arms

Surface electromyography (sEMG) is a popular bio-signal used for controlling prostheses and finger gesture recognition mechanisms. Myoelectric prostheses are costly, and most commercially available sEMG acquisition systems are not suitable for real-time gesture recognition. In this paper, a method of acquiring sEMG signals using novel low-cost, active, dry-contact, flexible sensors has been proposed. Since the active sEMG sensor was developed to be used along with a bionic arm, the sensor was tested for its ability to acquire sEMG signals that could be used for real-time classification of five selected gestures. In a study of 4 subjects, the average classification accuracy for real-time gesture classification using the active sEMG sensor system was 85%. The common-mode rejection ratio of the sensor was measured to 59 dB, and thus the sensor's performance was not substantially limited by its active circuitry. The proposed sensors can be interfaced with a variety of amplifiers to perform fully wearable sEMG acquisition. This satisfies the need for a low-cost sEMG acquisition system for prostheses.

cs.ET↗

arXiv2020

Real-Time Hand Gesture Recognition Using Temporal Muscle Activation Maps of Multi-Channel sEMG Signals

Accurate and real-time hand gesture recognition is essential for controlling advanced hand prostheses. Surface Electromyography (sEMG) signals obtained from the forearm are widely used for this purpose. Here, we introduce a novel hand gesture representation called Temporal Muscle Activation (TMA) maps which captures information about the activation patterns of muscles in the forearm. Based on these maps, we propose an algorithm that can recognize hand gestures in real-time using a Convolution Neural Network. The algorithm was tested on 8 healthy subjects with sEMG signals acquired from 8 electrodes placed along the circumference of the forearm. The average classification accuracy of the proposed method was 94%, which is comparable to state-of-the-art methods. The average computation time of a prediction was 5.5ms, making the algorithm ideal for the real-time gesture recognition applications.

eess.SP↗