While working on a software specification, designers usually need to evaluate different architectural alternatives to be sure that quality criteria are met. Even when these quality aspects could be expressed in terms of multiple software metrics, other qualitative factors cannot be numerically measured, but they are extracted from the engineer's know-how and prior experiences. In fact, detecting not only strong but also weak points in the different solutions seems to fit better with the way humans make their decisions. Putting the human in the loop brings new challenges to the search-based software engineering field, especially for those human-centered activities within the early analysis phase. This paper explores how the interactive evolutionary computation can serve as a basis for integrating the human's judgment into the search process. An interactive approach is proposed to discover software architectures, in which both quantitative and qualitative criteria are applied to guide a multi-objective evolutionary algorithm. The obtained feedback is incorporated into the fitness function using architectural preferences allowing the algorithm to discern between promising and poor solutions. Experimentation with real users has revealed that the proposed interaction mechanism can effectively guide the search towards those regions of the search space that are of real interest to the expert.
相關內容
Student modeling is central to many educational technologies as it enables predicting future learning outcomes and designing targeted instructional strategies. However, open-ended learning domains pose challenges for accurately modeling students due to the diverse behaviors and a large space of possible misconceptions. To approach these challenges, we explore the application of large language models (LLMs) for in-context student modeling in open-ended learning domains. More concretely, given a particular student's attempt on a reference task as observation, the objective is to synthesize the student's attempt on a target task. We introduce a novel framework, LLM for Student Synthesis (LLM-SS), that leverages LLMs for synthesizing a student's behavior. Our framework can be combined with different LLMs; moreover, we fine-tune LLMs to boost their student modeling capabilities. We instantiate several methods based on LLM-SS framework and evaluate them using an existing benchmark, StudentSyn, for student attempt synthesis in a visual programming domain. Experimental results show that our methods perform significantly better than the baseline method NeurSS provided in the StudentSyn benchmark. Furthermore, our method using a fine-tuned version of the GPT-3.5 model is significantly better than using the base GPT-3.5 model and gets close to human tutors' performance.
In many information processing systems, it may be desirable to ensure that any change of the input, whether by shifting or scaling, results in a corresponding change in the system response. While deep neural networks are gradually replacing all traditional automatic processing methods, they surprisingly do not guarantee such normalization-equivariance (scale + shift) property, which can be detrimental in many applications. To address this issue, we propose a methodology for adapting existing neural networks so that normalization-equivariance holds by design. Our main claim is that not only ordinary convolutional layers, but also all activation functions, including the ReLU (rectified linear unit), which are applied element-wise to the pre-activated neurons, should be completely removed from neural networks and replaced by better conditioned alternatives. To this end, we introduce affine-constrained convolutions and channel-wise sort pooling layers as surrogates and show that these two architectural modifications do preserve normalization-equivariance without loss of performance. Experimental results in image denoising show that normalization-equivariant neural networks, in addition to their better conditioning, also provide much better generalization across noise levels.
We show that (local) confluence of terminating locally constrained rewrite systems is undecidable, even when the underlying theory is decidable. Several confluence criteria for logically constrained rewrite systems are known. These were obtained by replaying existing proofs for plain term rewrite systems in a constrained setting, involving a non-trivial effort. We present a simple transformation from logically constrained rewrite systems to term rewrite systems such that critical pairs of the latter correspond to constrained critical pairs of the former. The usefulness of the transformation is illustrated by lifting the advanced confluence results based on (almost) development closed critical pairs as well as on parallel critical pairs to the constrained setting.
We analyze the operation of transformer language adapters, which are small modules trained on top of a frozen language model to adapt its predictions to new target languages. We show that adapted predictions mostly evolve in the source language the model was trained on, while the target language becomes pronounced only in the very last layers of the model. Moreover, the adaptation process is gradual and distributed across layers, where it is possible to skip small groups of adapters without decreasing adaptation performance. Last, we show that adapters operate on top of the model's frozen representation space while largely preserving its structure, rather than on an 'isolated' subspace. Our findings provide a deeper view into the adaptation process of language models to new languages, showcasing the constraints imposed on it by the underlying model and introduces practical implications to enhance its efficiency.
Advancements in technology are steering attention toward creating comfortable and acceptable driving characteristics in autonomous vehicles. Ensuring a safe and comfortable ride experience is vital for the widespread adoption of autonomous vehicles, as mismatches in driving styles between humans and autonomous systems can impact passenger confidence. Current driving functions have fixed parameters, and there is no universally agreed-upon driving style for autonomous vehicles. Integrating driving style preferences into automated vehicles may enhance acceptance and reduce uncertainty, expediting their adoption. A controlled vehicle study (N = 62) was conducted with a variety of German participants to identify the individual lateral driving behavior of human drivers, specifically emphasizing rural roads. We introduce novel indicators for assessing stationary and transient curve negotiation, directly applicable in developing personalized lateral driving functions. To assess the predictability of these indicators using self-reports, we introduce the MDSI-DE, the German version of the Multidimensional Driving Style Inventory. The correlation analysis between MDSI factor scores and proposed indicators showed modest but significant associations, primarily with acceleration and jerk statistics while the in-depth lateral driving behavior turned out to be highly driver-heterogeneous. The dataset including the anonymized socio-demographics and questionnaire responses, the raw vehicle measurements including labels, and the derived driving behavior indicators are publicly available at //www.kaggle.com/datasets/jhaselberger/spodb-subject-study-oflateral-vehicle-guidance.
Autoscaling is a technology to automatically scale the resources provided to their applications without human intervention to guarantee runtime Quality of Service (QoS) while saving costs. However, user-facing cloud applications serve dynamic workloads that often exhibit variable and contain bursts, posing challenges to autoscaling for maintaining QoS within Service-Level Objectives (SLOs). Conservative strategies risk over-provisioning, while aggressive ones may cause SLO violations, making it more challenging to design effective autoscaling. This paper introduces BAScaler, a Burst-Aware Autoscaling framework for containerized cloud services or applications under complex workloads, combining multi-level machine learning (ML) techniques to mitigate SLO violations while saving costs. BAScaler incorporates a novel prediction-based burst detection mechanism that distinguishes between predictable periodic workload spikes and actual bursts. When bursts are detected, BAScaler appropriately overestimates them and allocates resources accordingly to address the rapid growth in resource demand. On the other hand, BAScaler employs reinforcement learning to rectify potential inaccuracies in resource estimation, enabling more precise resource allocation during non-bursts. Experiments across ten real-world workloads demonstrate BAScaler's effectiveness, achieving a 57% average reduction in SLO violations and cutting resource costs by 10% compared to other prominent methods.
A growing number of safety-critical industries agree that building confidence in complex systems can be achieved through evidence and structured argumentation framed in assurance cases. Nevertheless, assurance cases can easily become too rigorous and difficult to develop and maintain when applied to complex systems. Therefore, we propose to use contract-based development (CBD), a method to manage complexity originally developed in computer science, to simplify assurance cases by modularizing them. This paper will not only summarize relevant previous work such as constructing consistent modular assurance cases using CBD, but more importantly also propose a novel approach to integrate CBD with the argumentation in assurance case modules. This approach will allow interdisciplinary subject-matter and domain experts to build assurance cases together without even knowing about CBD. This helps subject matter experts outside of computer science to reap benefits from CBD and helps with interdisciplinary co-development of assurance cases that cover all the required fields. This paper motivates four rules of thumb aimed to help practitioners developing high-quality modular assurance cases. It also explains how modularization of assurance is an enabler for multi-concern assurance that accounts for the inter-dependency of different concerns such as safety, security and performance.
As artificial intelligence (AI) models continue to scale up, they are becoming more capable and integrated into various forms of decision-making systems. For models involved in moral decision-making, also known as artificial moral agents (AMA), interpretability provides a way to trust and understand the agent's internal reasoning mechanisms for effective use and error correction. In this paper, we provide an overview of this rapidly-evolving sub-field of AI interpretability, introduce the concept of the Minimum Level of Interpretability (MLI) and recommend an MLI for various types of agents, to aid their safe deployment in real-world settings.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
Deep neural network architectures have traditionally been designed and explored with human expertise in a long-lasting trial-and-error process. This process requires huge amount of time, expertise, and resources. To address this tedious problem, we propose a novel algorithm to optimally find hyperparameters of a deep network architecture automatically. We specifically focus on designing neural architectures for medical image segmentation task. Our proposed method is based on a policy gradient reinforcement learning for which the reward function is assigned a segmentation evaluation utility (i.e., dice index). We show the efficacy of the proposed method with its low computational cost in comparison with the state-of-the-art medical image segmentation networks. We also present a new architecture design, a densely connected encoder-decoder CNN, as a strong baseline architecture to apply the proposed hyperparameter search algorithm. We apply the proposed algorithm to each layer of the baseline architectures. As an application, we train the proposed system on cine cardiac MR images from Automated Cardiac Diagnosis Challenge (ACDC) MICCAI 2017. Starting from a baseline segmentation architecture, the resulting network architecture obtains the state-of-the-art results in accuracy without performing any trial-and-error based architecture design approaches or close supervision of the hyperparameters changes.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191