Context: Forgetting is defined as a gradual process of losing information. Even though there are many studies demonstrating the effect of forgetting in software development, to the best of our knowledge, no study explores the impact of forgetting in software development using a controlled experiment approach. Objective: We would like to provide insights on the impact of forgetting in software development projects. We want to examine whether the recency & frequency of interaction impact forgetting in software development. Methods: We will conduct an experiment that examines the impact of forgetting in software development. Participants will first do an initial task. According to their initial task performance, they will be assigned to either the experiment or the control group. The experiment group will then do two additional tasks to enhance their exposure to the code. Both groups will then do a final task to see if additional exposure to the code benefits the experiment group's performance in the final task. Finally, we will conduct a survey and a recall task with the same participants to collect data about their perceptions of forgetting and quantify their memory performance, respectively.
相關內容
In experiments that study social phenomena, such as peer influence or herd immunity, the treatment of one unit may influence the outcomes of others. Such "interference between units" violates traditional approaches for causal inference, so that additional assumptions are often imposed to model or limit the underlying social mechanism. For binary outcomes, we propose an approach that does not require such assumptions, allowing for interference that is both unmodeled and strong, with confidence intervals derived using only the randomization of treatment. However, the estimates will have wider confidence intervals and weaker causal implications than those attainable under stronger assumptions. The approach allows for the usage of regression, matching, or weighting, as may best fit the application at hand. Inference is done by bounding the distribution of the estimation error over all possible values of the unknown counterfactual, using an integer program. Examples are shown using using a vaccination trial and two experiments investigating social influence.
The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework. However, performant CNN architectures must be tailored to specific tasks in order to incorporate considerations such as the input length, resolution, and dimentionality. In this work, we overcome the need for problem-specific CNN architectures with our Continuous Convolutional Neural Network (CCNN): a single CNN architecture equipped with continuous convolutional kernels that can be used for tasks on data of arbitrary resolution, dimensionality and length without structural changes. Continuous convolutional kernels model long range dependencies at every layer, and remove the need for downsampling layers and task-dependent depths needed in current CNN architectures. We show the generality of our approach by applying the same CCNN to a wide set of tasks on sequential (1$\mathrm{D}$) and visual data (2$\mathrm{D}$). Our CCNN performs competitively and often outperforms the current state-of-the-art across all tasks considered.
The creation and destruction of agents in cooperative multi-agent reinforcement learning (MARL) is a critically under-explored area of research. Current MARL algorithms often assume that the number of agents within a group remains fixed throughout an experiment. However, in many practical problems, an agent may terminate before their teammates. This early termination issue presents a challenge: the terminated agent must learn from the group's success or failure which occurs beyond its own existence. We refer to propagating value from rewards earned by remaining teammates to terminated agents as the Posthumous Credit Assignment problem. Current MARL methods handle this problem by placing these agents in an absorbing state until the entire group of agents reaches a termination condition. Although absorbing states enable existing algorithms and APIs to handle terminated agents without modification, practical training efficiency and resource use problems exist. In this work, we first demonstrate that sample complexity increases with the quantity of absorbing states in a toy supervised learning task for a fully connected network, while attention is more robust to variable size input. Then, we present a novel architecture for an existing state-of-the-art MARL algorithm which uses attention instead of a fully connected layer with absorbing states. Finally, we demonstrate that this novel architecture significantly outperforms the standard architecture on tasks in which agents are created or destroyed within episodes as well as standard multi-agent coordination tasks.
Reconfigurable intelligent surface (RIS) can effectively control the wavefront of the impinging signals and has emerged as a cost-effective promising solution to improve the spectrum and energy efficiency of wireless systems. Most existing researches on RIS assume that the hardware operations are perfect. However, both physical transceiver and RIS suffer from inevitable hardware impairments in practice, which can lead to severe system performance degradation and increase the complexity of beamforming optimization. Consequently, the existing researches on RIS, including channel estimation, beamforming optimization, spectrum and energy efficiency analysis, etc., cannot directly apply to the case of hardware impairments. In this paper, by taking hardware impairments into consideration, we conduct the joint transmit and reflect beamforming optimization, and reevaluate the system performance. First, we characterize the closed-form estimators of direct and cascaded channels in both single-user and multi-user cases, and analyze the impact of hardware impairments on channel estimation accuracy. Then, the optimal transmit beamforming solution is derived, and a gradient descent method-based algorithm is also proposed to optimize the reflect beamforming. Moreover, we analyze the three types of asymptotic channel capacities with respect to the transmit power, the antenna number, and the reflecting element number. Finally, in terms of the system energy consumption, we analyze the power scaling law and the energy efficiency. Our experimental results also reveal an encouraging phenomenon that the RIS-assisted wireless system with massive reflecting elements can achieve both high spectrum and energy efficiency without the need for massive antennas and without allocating too many resources to optimize the reflect beamforming.
A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much consideration for the human end-user. In particular, it is not yet known (1) how useful current explainability methods are in practice for more real-world scenarios and (2) how well associated performance metrics accurately predict how much knowledge individual explanations contribute to a human end-user trying to understand the inner-workings of the system. To fill this gap, we conducted psychophysics experiments at scale to evaluate the ability of human participants to leverage representative attribution methods for understanding the behavior of different image classifiers representing three real-world scenarios: identifying bias in an AI system, characterizing the visual strategy it uses for tasks that are too difficult for an untrained non-expert human observer as well as understanding its failure cases. Our results demonstrate that the degree to which individual attribution methods help human participants better understand an AI system varied widely across these scenarios. This suggests a critical need for the field to move past quantitative improvements of current attribution methods towards the development of complementary approaches that provide qualitatively different sources of information to human end-users.
Human-robot studies are expensive to conduct and difficult to control, and as such researchers sometimes turn to human-avatar interaction in the hope of faster and cheaper data collection that can be transferred to the robot domain. In terms of our work, we are particularly interested in the challenge of detecting and modelling user confusion in interaction, and as part of this research programme, we conducted situated dialogue studies to investigate users' reactions in confusing scenarios that we give in both physical and virtual environments. In this paper, we present a combined review of these studies and the results that we observed across these two embodiments. For the physical embodiment, we used a Pepper Robot, while for the virtual modality, we used a 3D avatar. Our study shows that despite attitudinal differences and technical control limitations, there were a number of similarities detected in user behaviour and self-reporting results across embodiment options. This work suggests that, while avatar interaction is no true substitute for robot interaction studies, sufficient care in study design may allow well executed human-avatar studies to supplement more challenging human-robot studies.
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern 1) a taxonomy and extensive overview of the state-of-the-art, 2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner, 3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time, and storage.
Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: `Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE: Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyze the efficacy of ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-of-the-art performance, with no extra methodological effort. We hope that our work will attract further research into this newly identified, yet crucial research direction.
It has been a long time that computer architecture and systems are optimized to enable efficient execution of machine learning (ML) algorithms or models. Now, it is time to reconsider the relationship between ML and systems, and let ML transform the way that computer architecture and systems are designed. This embraces a twofold meaning: the improvement of designers' productivity, and the completion of the virtuous cycle. In this paper, we present a comprehensive review of work that applies ML for system design, which can be grouped into two major categories, ML-based modelling that involves predictions of performance metrics or some other criteria of interest, and ML-based design methodology that directly leverages ML as the design tool. For ML-based modelling, we discuss existing studies based on their target level of system, ranging from the circuit level to the architecture/system level. For ML-based design methodology, we follow a bottom-up path to review current work, with a scope of (micro-)architecture design (memory, branch prediction, NoC), coordination between architecture/system and workload (resource allocation and management, data center management, and security), compiler, and design automation. We further provide a future vision of opportunities and potential directions, and envision that applying ML for computer architecture and systems would thrive in the community.
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