Prasad Kawthekar

Modern software systems are built to be used in dynamic environments using configuration capabilities to adapt to changes and external uncertainties. In a self-adaptation context, we are often interested in reasoning about the performance of the systems under different configurations. Usually, we learn a black box model based on real measurements to predict the performance of the system given a specific configuration. However, as modern systems become more complex, there are many configuration… Show more

Modern software systems are built to be used in dynamic environments using configuration capabilities to adapt to changes and external uncertainties. In a self-adaptation context, we are often interested in reasoning about the performance of the systems under different configurations. Usually, we learn a black box model based on real measurements to predict the performance of the system given a specific configuration. However, as modern systems become more complex, there are many configuration parameters that may interact and we end up learning an exponentially large configuration space. Naturally, this does not scale when relying on real measurements in the actual changing environment. We propose a different solution: Instead of taking the measurements from the real system, we learn the model using samples from other sources, such as simulators that approximate performance of the real system at low cost. We define a cost model that transform the traditional view of model learning into a multi-objective problem that not only takes into account model accuracy but also measurements effort as well. We evaluate our cost-aware transfer learning solution using real-world configurable software including (i) a robotic system, (ii) 3 different stream processing applications, and (iii) a NoSQL database system. The experimental results demonstrate that our approach can achieve (a) a high prediction accuracy, as well as (b) a high model reliability. Show less

Massively parallel reporter assays (MPRAs) are a method to probe the effects of short sequences on transcriptional regulation activity. In a MPRA, short sequences are extracted from suspected regulatory regions, inserted into reporter plasmids, transfected into cell-types of interest, and the transcriptional activity of each reporter is assayed. Recently, Ernst et al. presented MPRA data covering 15750 putative regulatory regions. We trained a multitask convolutional neural network architecture… Show more

Massively parallel reporter assays (MPRAs) are a method to probe the effects of short sequences on transcriptional regulation activity. In a MPRA, short sequences are extracted from suspected regulatory regions, inserted into reporter plasmids, transfected into cell-types of interest, and the transcriptional activity of each reporter is assayed. Recently, Ernst et al. presented MPRA data covering 15750 putative regulatory regions. We trained a multitask convolutional neural network architecture using these sequence expression readouts which predicts as output the expression level outputs across four combinations of cell types and promoters. The model allows for the assigning of importance scores to each base through in silico mutagenesis, and the resulting importance scores correlated well with regions enriched for conservation and transcription factor binding. Show less

There has been a considerable growth in research and development of service robots in recent years. For deployment in diverse environment conditions for a wide range of service tasks, novel features and algorithms are developed and existing ones undergo change. However, developing and evolving the robot software requires making and revising many design decisions that can affect the quality of performance of the robots and that are non-trivial to reason about intuitively because of interactions… Show more

There has been a considerable growth in research and development of service robots in recent years. For deployment in diverse environment conditions for a wide range of service tasks, novel features and algorithms are developed and existing ones undergo change. However, developing and evolving the robot software requires making and revising many design decisions that can affect the quality of performance of the robots and that are non-trivial to reason about intuitively because of interactions among them. We propose to use sensitivity analysis to build models of the quality of performance to the different design decisions to ease design and evolution. Moreover, we envision these models to be used for run-time adaptation in response to changing goals or environment conditions. Constructing these models is challenging due to the exponential size of the decision space. We build on previous work on performance influence models of highly-configurable software systems using a machine-learning-based approach to construct influence models for robotic software. Show less