While artificial intelligence (AI) models have improved at understanding large-scale data, understanding AI models themselves at any scale is difficult. For example, even two models that implement the same network architecture may differ in frameworks, datasets, or even domains. Furthermore, attempting to use either model often requires much manual effort to understand it. As software engineering and AI development share many of the same languages and tools, techniques in mining software repositories should enable more scalable insights into AI models and AI development. However, much of the relevant metadata around models are not easily extractable. This paper (an extension of our MSR 2020 paper) presents a library called AIMMX for AI Model Metadata eXtraction from software repositories into enhanced metadata that conforms to a flexible metadata schema. We evaluated AIMMX against 7,998 open-source models from three sources: model zoos, arXiv AI papers, and state-of-the-art AI papers. We also explored how AIMMX can enable studies and tools to advance engineering support for AI development. As preliminary examples, we present an exploratory analysis for data and method reproducibility over the models in the evaluation dataset and a catalog tool for discovering and managing models. We also demonstrate the flexibility of extracted metadata by using the evaluation dataset in an existing natural language processing (NLP) analysis platform to identify trends in the dataset. Overall, we hope AIMMX fosters research towards better AI development.

Background: Assistive automatic seizure detection can empower human annotators to shorten patient monitoring data review times. We present a proof-of-concept for a seizure detection system that is sensitive, automated, patient-specific, and tunable to maximise sensitivity while minimizing human annotation times. The system uses custom data preparation methods, deep learning analytics and electroencephalography (EEG) data. Methods: Scalp EEG data of 365 patients containing 171,745 s ictal and 2,185,864 s interictal samples obtained from clinical monitoring systems were analysed as part of a crowdsourced artificial intelligence (AI) challenge. Participants were tasked to develop an ictal/interictal classifier with high sensitivity and low false alarm rates. We built a challenge platform that prevented participants from downloading or directly accessing the data while allowing crowdsourced model development. Findings: The automatic detection system achieved tunable sensitivities between 75.00% and 91.60% allowing a reduction in the amount of raw EEG data to be reviewed by a human annotator by factors between 142x, and 22x respectively. The algorithm enables instantaneous reviewer-managed optimization of the balance between sensitivity and the amount of raw EEG data to be reviewed. Interpretation: This study demonstrates the utility of deep learning for patient-specific seizure detection in EEG data. Furthermore, deep learning in combination with a human reviewer can provide the basis for an assistive data labelling system lowering the time of manual review while maintaining human expert annotation performance. Funding: IBM employed all IBM Research authors. Temple University employed all Temple University authors. The Icahn School of Medicine at Mount Sinai employed Eren Ahsen. The corresponding authors Stefan Harrer and Gustavo Stolovitzky declare that they had full access to all the data in the study and that they had final responsibility for the decision to submit for publication.

ABSTRACTDespite all of the power that machine learning and artificial intelligence (AI) models bring to applications, much of AI development is currently a fairly ad hoc process. Software engineering and AI development share many of the same languages and tools, but AI development as an engineering practice is still in early stages. Mining software repositories of AI models enables insight into the current state of AI development. However, much of the relevant metadata around models are not easily extractable directly from repositories and require deduction or domain knowledge. This paper presents a library called AIMMX that enables simplified AI Model Metadata eXtraction from software repositories. The extractors have five modules for extracting AI model-specific metadata: model name, associated datasets, references, AI frameworks used, and model domain. We evaluated AIMMX against 7,998 open-source models from three sources: model zoos, arXiv AI papers, and state-of-the-art AI papers. Our platform extracted metadata with 87% precision and 83% recall. As preliminary examples of how AI model metadata extraction enables studies and tools to advance engineering support for AI development, this paper presents an exploratory analysis for data and method reproducibility over the models in the evaluation dataset and a catalog tool for discovering and managing models. Our analysis suggests that while data reproducibility may be relatively poor with 42% of models in our sample citing their datasets, method reproducibility is more common at 72% of models in our sample, particularly state-of-the-art models. Our collected models are searchable in a catalog that uses existing metadata to enable advanced discovery features for efficiently finding models.

Background Assistive automatic seizure detection can empower human annotators to shorten patient monitoring data review times. We present a proof-of-concept for Findings The automatic detection system achieved tunable sensitivities between 75.00% and 91.60% allowing to reduce the amount of raw EEG data to be reviewed by a human annotator by factors between 142x, and 22x respectively. The algorithm enables instantaneous reviewer-managed optimisation of the balance between sensitivity and the amount of raw EEG data to be reviewed. Interpretation This study demonstrates the utility of deep learning for patient-specific seizure detection in EEG data. Furthermore, deep learning in combination with a human reviewer can provide the basis for an assistive data labelling system lowering the time of manual review while maintaining human expert annotation performance. the data in the study that they final for the to for publication.

Today's cloud service architectures follow a “one size fits all” deployment strategy where the same service version instantiation is provided to the end users. However, consumers are broad and different applications have different accuracy and responsiveness requirements, which as we demonstrate renders the “one size fits all” approach inefficient in practice. We use a production grade speech recognition engine, which serves several thousands of users, and an open source computer vision based system, to explain our point. To overcome the limitations of the “one size fits all” approach, we recommend Tolerance Tiers where each MLaaS tier exposes an accuracy/responsiveness characteristic, and consumers can programmatically select a tier. We evaluate our proposal on the CPU-based automatic speech recognition (ASR) engine and cutting-edge neural networks for image classification deployed on both CPUs and GPUs. The results show that our proposed approach provides a MLaaS cloud service architecture that can be tuned by the end API user or consumer to outperform the conventional “one size fits all” approach.

Runway is a cloud-native tool for managing machine learning experiments and their associated models. The iterative nature of developing models results in a large number of experiments and models that are often managed in an ad hoc manner. Runway is a workflow and framework independent tool that centrally manages and maintains metadata and links to artifacts needed to reproduce models and experiments. Runway provides a web dashboard with multiple levels of visualizations to evaluate performance and enable side-by-side comparisons of models and experiments.

Cognitive cloud services seek to provide end-users with functionalities that have historically required human intellect to complete. End-users expect these services to be both responsive and accurate, which pose conflicting requirements for service providers. Today’s cloud services deployment schemes follow a “one size fits all” scale-out strategy, where multiple instantiations of the same version of the service are used to scale-out and handle all end-users. Meanwhile, many cognitive services are of a statistical nature where deeper exploration yields more accurate results but also requires more processing time. Finding a single service configuration setting that satisfies the latency and accuracy requirements for the largest number of expected end-user requests can be a challenging task. As a result, cognitive cloud service providers are conservatively configured to maximize the number of enduser requests for which a satisfactory latency-accuracy tradeoff can be achieved. Using a production-grade Automatic Speech Recognition cloud service as a representative example to study, we demonstrate the inefficiencies of this single version approach and propose a new service node multi-versioning deployment scheme for cognitive services instead. We present an oracle-based limit study where we show that service node multi-versioning can provide a 2.5X reduction in execution time together with a 24% improvement in accuracy over a traditional single version deployment scheme. We also discuss several design considerations to address when implementing service node multi-versioning.

The dramatic proliferation of virtual machines (VMs) in datacenters and the highly-dynamic and transient nature of VM provisioning has revolutionized datacenter operations. However, the management of these environments is still carried out using re-purposed versions of traditional agents, originally developed for managing physical systems, or most recently via newer virtualization-aware alternatives that require guest cooperation and accessibility. We show that these existing approaches are a poor match for monitoring and managing (virtual) systems in the cloud due to their dependence on guest cooperation and operational health, and their growing lifecycle management overheads in the cloud. In this work, we first present Near Field Monitoring (NFM), our non-intrusive, out-of-band cloud monitoring and analytics approach that is designed based on cloud operation principles and to address the limitations of existing techniques. NFM decouples system execution from monitoring and analytics functions by pushing monitoring out of the targets systems' scope. By leveraging and extending VM introspection techniques, our framework provides simple, standard interfaces to monitor running systems in the cloud that require no guest cooperation or modification, and have minimal effect on guest execution. By decoupling monitoring and analytics from target system context, NFM provides ``always-on'' monitoring, even when the target system is unresponsive. NFM also works ``out-of-the-box'' for any cloud instance as it eliminates any need for installing and maintaining agents or hooks in the monitored systems. We describe the end-to-end implementation of our framework with two real-system prototypes based on two virtualization platforms. We discuss the new cloud analytics opportunities enabled by our decoupled execution, monitoring and analytics architecture. We present four applications that are built on top of our framework and show their use for across-time and across-system analytics.