Live programming is a paradigm in which the programming environment continually displays runtime values. Program synthesis is a technique that can generate programs or program snippets from examples. \deltextThis paper presents a new programming paradigm called Synthesis-Aided Live Programming that combines these two prior ideas in a synergistic way. When using Synthesis-Aided Live Programming, programmers can change the runtime values displayed by the live \addtextPrevious works that combine the two have taken a holistic approach to the way examples describe the behavior of functions and programs. This paper presents a new programming paradigm called Small-Step Live Programming by Example that lets the user apply Programming by Example locally. When using Small-Step Live Programming by Example, programmers can change the runtime values displayed by the live visualization to generate local program snippets. % Live programming and program % synthesis work perfectly together because the live programming environment % reifies values, which makes it easy for programmers to provide the examples % needed by the synthesizer. We implemented this new paradigm in a tool called \toolname, and performed a user study on $13$ programmers. Our study finds that Small-Step Live Programming by Example with \toolname helps users solve harder problems faster, and that for certain types of queries, users prefer it to searching the web. Additionally, we identify the \usersynthgap, in which users' mental models of the tool do not match its ability, and needs to be taken into account in the design of future synthesis tools.

In this demonstration, we present Krypton, a system for accelerating occlusion-based deep convolution neural network (CNN) explanation workloads. Driven by the success of CNNs in image understanding tasks, there is growing adoption of CNNs in various domains, including high stakes applications such as radiology. However, users of such applications often seek an "explanation" for why a CNN predicted a certain label. One of the most widely used approaches for explaining CNN predictions is the occlusion-based explanation (OBE) method. This approach is computationally expensive due to the large number of re-inference requests produced. Krypton reduces the runtime of OBE by up to 35x by enabling incremental and approximate inference optimizations that are inspired by classical database query optimization techniques. We allow the audience to interactively diagnose CNN predictions from several use cases, including radiology and natural images. A short video of our demonstration can be found here: https://youtu.be/1OWddbd4n6Y