Suat Gumussoy

Quoc Tran Dinh, Suat Gumussoy, Wim Michiels et al.

A novel optimization method is proposed to minimize a convex function subject to bilinear matrix inequality (BMI) constraints. The key idea is to decompose the bilinear mapping as a difference between two positive semidefinite convex mappings. At each iteration of the algorithm the concave part is linearized, leading to a convex subproblem.Applications to various output feedback controller synthesis problems are presented. In these applications the subproblem in each iteration step can be turned into a convex optimization problem with linear matrix inequality (LMI) constraints. The performance of the algorithm has been benchmarked on the data from COMPleib library.

Toygun Basaklar, Suat Gumussoy, Umit Y. Ogras

Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given domain with a single training is critical. To this end, we propose a novel MORL algorithm that trains a single universal network to cover the entire preference space scalable to continuous robotic tasks. The proposed approach, Preference-Driven MORL (PD-MORL), utilizes the preferences as guidance to update the network parameters. It also employs a novel parallelization approach to increase sample efficiency. We show that PD-MORL achieves up to 25% larger hypervolume for challenging continuous control tasks and uses an order of magnitude fewer trainable parameters compared to prior approaches.

Ganapati Bhat, Suat Gumussoy, Umit Y. Ogras

Modern multiprocessor system-on-chips (SoCs) integrate multiple heterogeneous cores to achieve high energy efficiency. The power consumption of each core contributes to an increase in the temperature across the chip floorplan. In turn, higher temperature increases the leakage power exponentially, and leads to a positive feedback with nonlinear dynamics. This paper presents a power-temperature stability and safety analysis technique for multiprocessor systems. This analysis reveals the conditions under which the power-temperature trajectory converges to a stable fixed point. We also present a simple formula to compute the stable fixed point and maximum thermally-safe power consumption at runtime. Hardware measurements on a state-of-the-art mobile processor show that our analytical formulation can predict the stable fixed point with an average error of 2.6%. Hence, our approach can be used at runtime to ensure thermally safe operation and guard against thermal threats.

Suat Gumussoy, Murad Abu-Khalaf

The solvability of a delay differential equation arising in the construction of quadratic cost functionals, i.e. Lyapunov functionals, for a linear time-delay system with a constant and a distributed delay is investigated. We present a delay-free auxiliary ordinary differential equation system with algebraically coupled split-boundary conditions, that characterizes the solutions of the delay differential equation and is used for solution synthesis. A spectral property of the time-delay system yields a necessary and sufficient condition for existence and uniqueness of solutions to the auxiliary system, equivalently the delay differential equation. The result is a tractable analytic solution framework to the delay differential equation.

Murad Abu-Khalaf, Suat Gumussoy

We prove that an auxiliary two-point boundary value problem presented in V. L. Kharitonov, Lyapunov matrices for a class of time delay systems, Systems & Control Letters 55 (2006) 610-617 has linearly dependent boundary conditions, and consequently a unique solution does not exist. Therefore, the two-point boundary value problem presented therein fails to be a basis for constructing Lyapunov matrices for the class of time delay systems investigated.

Toygun Basaklar, Yigit Tuncel, Shruti Yadav Narayana et al.

Hyperdimensional computing (HDC) has emerged as a new light-weight learning algorithm with smaller computation and energy requirements compared to conventional techniques. In HDC, data points are represented by high-dimensional vectors (hypervectors), which are mapped to high-dimensional space (hyperspace). Typically, a large hypervector dimension ($\geq1000$) is required to achieve accuracies comparable to conventional alternatives. However, unnecessarily large hypervectors increase hardware and energy costs, which can undermine their benefits. This paper presents a technique to minimize the hypervector dimension while maintaining the accuracy and improving the robustness of the classifier. To this end, we formulate the hypervector design as a multi-objective optimization problem for the first time in the literature. The proposed approach decreases the hypervector dimension by more than $32\times$ while maintaining or increasing the accuracy achieved by conventional HDC. Experiments on a commercial hardware platform show that the proposed approach achieves more than one order of magnitude reduction in model size, inference time, and energy consumption. We also demonstrate the trade-off between accuracy and robustness to noise and provide Pareto front solutions as a design parameter in our hypervector design.

Sizhe An, Ganapati Bhat, Suat Gumussoy et al.

Human activity recognition (HAR) research has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with known users and then using the same classifier for new users. However, the accuracy for new users can be low with this approach if their activity patterns are different than those in the training data. At the same time, training from scratch for new users is not feasible for mobile applications due to the high computational cost and training time. To address this issue, we propose a HAR transfer learning framework with two components. First, a representational analysis reveals common features that can transfer across users and user-specific features that need to be customized. Using this insight, we transfer the reusable portion of the offline classifier to new users and fine-tune only the rest. Our experiments with five datasets show up to 43% accuracy improvement and 66% training time reduction when compared to the baseline without using transfer learning. Furthermore, measurements on the Nvidia Jetson Xavier-NX hardware platform reveal that the power and energy consumption decrease by 43% and 68%, respectively, while achieving the same or higher accuracy as training from scratch.