L. R. Medsker

Bio: L. R. Medsker is an academic researcher. The author has contributed to research in topics: Recurrent neural network & Wish. The author has an hindex of 1, co-authored 1 publications receiving 445 citations.

Recurrent Neural Networks: Design and Applications

Abstract: From the Publisher: With applications ranging from motion detection to financial forecasting, recurrent neural networks (RNNs) have emerged as an interesting and important part of neural network research. Recurrent Neural Networks: Design and Applications reflects the tremendous, worldwide interest in and virtually unlimited potential of RNNs - providing a summary of the design, applications, current research, and challenges of this dynamic and promising field.

SIGAI Annual Report: July 1 2021 - June 30 2022

Abstract: We are delighted to share our annual report with membership. This highlights some of the many activities we do as a SIG, and could provide some inspiration for members who wish to get more involved about the types of activities they could participate in or where they feel new initiatives might be most welcome. If you are interested in being more involved with SIGAI or have ideas for future initiatives, please reach out to any or all of the leadership team.

DeepTest: automated testing of deep-neural-network-driven autonomous cars

Abstract: Recent advances in Deep Neural Networks (DNNs) have led to the development of DNN-driven autonomous cars that, using sensors like camera, LiDAR, etc., can drive without any human intervention. Most major manufacturers including Tesla, GM, Ford, BMW, and Waymo/Google are working on building and testing different types of autonomous vehicles. The lawmakers of several US states including California, Texas, and New York have passed new legislation to fast-track the process of testing and deployment of autonomous vehicles on their roads. However, despite their spectacular progress, DNNs, just like traditional software, often demonstrate incorrect or unexpected corner-case behaviors that can lead to potentially fatal collisions. Several such real-world accidents involving autonomous cars have already happened including one which resulted in a fatality. Most existing testing techniques for DNN-driven vehicles are heavily dependent on the manual collection of test data under different driving conditions which become prohibitively expensive as the number of test conditions increases. In this paper, we design, implement, and evaluate DeepTest, a systematic testing tool for automatically detecting erroneous behaviors of DNN-driven vehicles that can potentially lead to fatal crashes. First, our tool is designed to automatically generated test cases leveraging real-world changes in driving conditions like rain, fog, lighting conditions, etc. DeepTest systematically explore different parts of the DNN logic by generating test inputs that maximize the numbers of activated neurons. DeepTest found thousands of erroneous behaviors under different realistic driving conditions (e.g., blurring, rain, fog, etc.) many of which lead to potentially fatal crashes in three top performing DNNs in the Udacity self-driving car challenge.

Optimization of fused deposition modeling process parameters: a review of current research and future prospects

Abstract: Fused deposition modeling (FDM) is one of the most popular additive manufacturing technologies for various engineering applications. FDM process has been introduced commercially in early 1990s by Stratasys Inc., USA. The quality of FDM processed parts mainly depends on careful selection of process variables. Thus, identification of the FDM process parameters that significantly affect the quality of FDM processed parts is important. In recent years, researchers have explored a number of ways to improve the mechanical properties and part quality using various experimental design techniques and concepts. This article aims to review the research carried out so far in determining and optimizing the process parameters of the FDM process. Several statistical designs of experiments and optimization techniques used for the determination of optimum process parameters have been examined. The trends for future FDM research in this area are described.

Statistical and Machine Learning forecasting methods: Concerns and ways forward.

Abstract: Machine Learning (ML) methods have been proposed in the academic literature as alternatives to statistical ones for time series forecasting. Yet, scant evidence is available about their relative performance in terms of accuracy and computational requirements. The purpose of this paper is to evaluate such performance across multiple forecasting horizons using a large subset of 1045 monthly time series used in the M3 Competition. After comparing the post-sample accuracy of popular ML methods with that of eight traditional statistical ones, we found that the former are dominated across both accuracy measures used and for all forecasting horizons examined. Moreover, we observed that their computational requirements are considerably greater than those of statistical methods. The paper discusses the results, explains why the accuracy of ML models is below that of statistical ones and proposes some possible ways forward. The empirical results found in our research stress the need for objective and unbiased ways to test the performance of forecasting methods that can be achieved through sizable and open competitions allowing meaningful comparisons and definite conclusions.