Abstract

In this paper, we design and develop a hardware accelerator for computing the LU decomposition of an input matrix. Our accelerator consists of two simple linear arrays of Processing Engines (PEs), one on each of the two SLR regions of the FPGA. All the computations arising from the block LU decomposition are simplified and scheduled on these two PE arrays. On an Alveo U50 FPGA, our design achieves a peak floating-point performance of 128 GLOPS/s and an average performance of 95 GFLOPS/s. We achieve ≈ 15× speedup on latency compared to an Intel MKL implementation on a 4-core Intel Xeon CPU.

Abstract

First Order Bayesian Optimization (FOBO) is a sample efficient sequential approach to find the global maxima of an expensive-to-evaluate black-box objective function by suitably querying for the function and its gradient evaluations. Such methods assume Gaussian process (GP) models for both, the function and its gradient, and use them to construct an acquisition function that identifies the next query point. In this paper, we propose a class of practical FOBO algorithms that efficiently utilizes the information from the gradient GP to identify potential query points with zero gradients. We construct a multi-level acquisition function where in the first step, we optimize a lower level acquisition function with multiple restarts to identify potential query points with zero gradient value. We then use the upper level acquisition function to rank these query points based on their function values to potentially identify the global maxima. As a final step, the potential point of maxima is chosen as the actual query point. We validate the performance of our proposed algorithms on several test functions and show that our algorithms outperform state-of-the-art FOBO algorithms. We also illustrate the application of our algorithms in finding optimal set of hyper-parameters in machine learning and in learning the optimal policy in reinforcement learning tasks.

Abstract

In this work, we explore the enhancement of sensitivity of sensing of biomolecules using Radio Frequency (RF) based sensing, by utilizing gold particles. In particular, we investigate the impact of various parameters of gold particles such as shape, size and arrangements on enhancing sensitivity. The work uses a Microstrip Patch Antenna designed to resonate at 96.84 GHz. The sensor is facile, rapid and efficient, and uses sample volume of 17.5 nL. The results indicate that the presence of gold particles helps in improving the performance of RF sensors in detecting biomolecules. However, the extent of improvement depends on the properties of gold particles and is in the range of 30-80% for the different cases studied in this work.

Abstract

The generation of low-energy 3D structures of metal clusters depends on the efficiency of the search algorithm and the accuracy of inter-atomic interaction description. In this work, we formulate the search algorithm as a Reinforcement Learning (RL) problem. Concisely, we propose a novel actor-critic architecture that generates low-lying isomers of metal clusters at a fraction of computational cost than conventional methods. Our RL-based search algorithm uses a previously developed DART model as a reward function to describe the inter-atomic interactions to validate predicted structures. Using the DART model as a reward function incentivizes the RL model to generate low-energy structures and helps generate valid structures. We demonstrate the advantages of our approach over conventional methods for scanning local minima on potential energy surface (PES). Our approach not only generates isomer of

Abstract

The goal of drug discovery is to uncover new molecules with specific chemical properties that can be used to cure diseases. With the accessibility of machine learning techniques, the approach used in this search has become a significant component in computer science in recent years. To meet the Precision Medicine Initiative’s goals and the additional obstacles that they have created, it is vital to develop strong, consistent, and repeatable computational approaches. Predictive models based on machine learning are becoming increasingly crucial in preclinical investigations. In discovering novel pharmaceuticals, this step substantially reduces expenses and research times. The human kinome contains various kinase enzymes that play vital roles through catalyzing protein phosphorylation. Interestingly, the dysregulation of kinases causes various human diseases, viz., cancer, cardiovascular disease, and several neuro-degenerative disorders. Thus, inhibitors of specific kinases can treat those diseases through blocking their activity as well as restoring normal cellular signaling. This review article discusses recent advancements in computational drug design algorithms through machine learning and deep learning and the computational drug design of kinase enzymes. Analyzing the current state-of-the-art in this sector will offer us a sense of where cheminformatics may evolve in the near future and the limitations and beneficial outcomes it has produced. The approaches utilized to model molecular data, the biological problems addressed, and the machine learning algorithms employed for drug discovery in recent years will be the emphasis of this review.

Abstract

An evident challenge ahead for the integrated circuit (IC) industry is the investigation and development of methods to reduce the design complexity ensuing from growing process variations and curtail the turnaround time of chip manufacturing. Conventional methodologies employed for such tasks are largely manual, timeconsuming, and resource-intensive. In contrast, the unique learning strategies of artificial intelligence (AI) provide numerous exciting automated approaches for handling complex and data-intensive tasks in very-largescale integration (VLSI) design and testing. Employing AI and machine learning (ML) algorithms in VLSI design and manufacturing reduces the time and effort for understanding and processing the data within and across different abstraction levels. It, in turn, improves the IC yield and reduces the manufacturing turnaround time. This paper thoroughly reviews the AI/ML automated approaches introduced in the past toward VLSI design and manufacturing. Moreover, we discuss the future scope of AI/ML applications to revolutionize the field of VLSI design, aiming for high-speed, highly intelligent, and efficient implementations.

Abstract

An Integrated Circuit with an automatically re-tuning analog circuit is provided. The Integrated Circuit comprises (a) an analog circuit comprising a plurality of tunable components each configured to respond to a plurality of change control bits, (b) a Process, Voltage Temperature (PVT) characteristics monitor comprising a plurality of PVT sensors, (c) a tuning memory embedded with a machine learning (ML) model of the analog circuit and (d) an artificial intelligence (AI) engine configured to receive a PVT signal input from the plurality of PVT sensors and the machine learning model embedded in the tuning memory. Each tunable component is configured to change its electrical characteristics such that together each of the tunable components is enabled to retune the analog circuit to attain a predefined set of electrical characteristics.

Abstract

Classification of a motorcycle's driving events can provide deep insights to detect issues related to driver safety. In order to perform the above, we developed a hardware system with 3-D accelerometer/gyroscope sensors that can be deployed on a motorcycle. The data obtained from these sensors is used to identify various driving events. We firstly investigated several machine learning (ML) models to classify driving events. However, in this process, we identified that though the overall accuracy of these traditional ML models is decent enough, the class-wise accuracy of these models is poor. Hence, we have developed time-series-based classification algorithms using LSTM and Bi-LSTM to classify various driving events. The experiments conducted have demonstrated that the proposed models have surpassed the state-of-the-art models in the context of driving event recognition with better class-wise accuracies …

Abstract

This paper presents a knowledge-driven approach for automated synthesis of controllers in three different use-cases. The approach addresses the engineering challenge posed by Industrie 4.0, which requires fast, reliable, and flexible integration of multiple heterogeneous hardware and software components. Manual design approaches are not scalable for large systems due to their complexity. The proposed approach captures resource-capability knowledge and uses a reasoning-based synthesis mechanism to compose a controller design for a plant goal. The approach uses domain-specific languages (DSLs) to describe the components, their interfaces, and capabilities. The generated control designs are executable codes that implement the control strategy. The proposed approach reduces the average engineering time by 70% and generates on an average 60% of the executable code in each use-case. The

Abstract

Interactive computer systems’ designers emphasize the importance of considering humans, their emotions, and behaviors as first-class entities. Emotions are integral parts of human nature, and ignoring that can lead the interactive systems to failure, low quality, or discomfort. User interfaces (UIs) are increasingly becoming adaptive to users’ various characteristics, intending to improve users’ satisfaction, performance, and decisions. However, the previous approaches proposed for supervising such adaptations are not effectively adopted in real-life problems. This paper proposes the novel approach to adapting UIs to users’ emotions using Model-Free Reinforcement Learning (MFRL). The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users’ task completion and satisfaction. We chose emergency evacuation training as a suitable evaluation domain since people experience intense emotions in potential danger. We performed experiments with a mobile application we developed that acts as a recommender system in emergency training. By taking contextual input of the users’ basic emotions from face recognition, the application intelligently adapts its UI to quickly lead people to safe areas while arousing target emotions. The research includes literature analysis, surveys, and further adopting an iterative process in implementation and experimentation. The evaluation process confirms the efficiency and effectiveness of the MFRL in iterations, as well as compared to other possible UI adaptation techniques, i.e., rule-based and sequential adaptation.