Requirements elicitation interviews are a widely adopted technique, where the interview success heavily depends on the interviewer's preparedness and communication skills. Students can enhance these skills through practice interviews. However, organizing practice interviews for many students presents scalability challenges, given the time and effort required to involve stakeholders in each session. To address this, we propose REIT, an extensible architecture for Requirements Elicitation Interview Training system based on emerging educational technologies. REIT has components to support both the interview phase, wherein students act as interviewers while the system assumes the role of an interviewee, and the feedback phase, during which the system assesses students' performance and offers contextual and behavioral feedback to enhance their interviewing skills. We demonstrate the applicability of REIT through two implementations: RoREIT with a physical robotic agent and VoREIT with a virtual voice-only agent. We empirically evaluated both instances with a group of graduate students. The participants appreciated both systems. They demonstrated higher learning gain when trained with RoREIT, but they found VoREIT more engaging and easier to use. These findings indicate that each system has distinct benefits and drawbacks, suggesting that REIT can be realized for various educational settings based on preferences and available resources.

A bipartisan panel of voters weighed in on the future of artificial intelligence and growing concerns surrounding the potential dangers of the emerging technology. A U.K.-based tech expert said he is not losing sleep at night over the recent growth of artificial intelligence but argued he does have concerns over AI potentially becoming a hellish boss that oversees an employee's every move. Michael Wooldridge is a professor of computer science at the University of Oxford who has been a leading expert on AI for at least 30 years. He spoke with The Guardian this month regarding upcoming lectures he will lead this winter to demystify artificial intelligence, while noting what concerns he does have with the tech. He told the outlet that he does not share the same worries as some AI experts who warn the powerful systems could one day lead to the downfall of humanity.

Existing information on AI-based facial emotion recognition (FER) is not easily comprehensible by those outside the field of computer science, requiring cross-disciplinary effort to determine a categorisation framework that promotes the understanding of this technology, and its impact on users. Most proponents classify FER in terms of methodology, implementation and analysis; relatively few by its application in education; and none by its users. This paper is concerned primarily with (potential) teacher-users of FER tools for education. It proposes a three-part classification of these teachers, by orientation, condition and preference, based on a classical taxonomy of affective educational objectives, and related theories. It also compiles and organises the types of FER solutions found in or inferred from the literature into "technology" and "applications" categories, as a prerequisite for structuring the proposed "teacher-user" category. This work has implications for proponents', critics', and users' understanding of the relationship between teachers and FER.

Benefiting from the powerful capabilities of large language models (LLMs), agents based on LLMs have shown the potential to address domain-specific tasks and emulate human behaviors. However, the content generated by these agents remains somewhat superficial, owing to their limited domain expertise and the absence of an effective cognitive architecture. To address this, we present the Configurable General Multi-Agent Interaction (CGMI) framework, designed to replicate human interactions in real-world scenarios. Specifically, we propose a tree-structured methodology for the assignment, detection, and maintenance of agent personality. Additionally, we designed a cognitive architecture equipped with a skill library based on the ACT* model, which contains memory, reflection, and planning modules. We have also integrated general agents to augment the virtual environment's realism. Using the CGMI framework, we simulated numerous classroom interactions between teacher and students. The experiments indicate that aspects such as the teaching methodology, curriculum, and student performance closely mirror real classroom settings. We will open source our work.

These lecture notes provide an overview of existing methodologies and recent developments for estimation and inference with high dimensional time series regression models. First, we present main limit theory results for high dimensional dependent data which is relevant to covariance matrix structures as well as to dependent time series sequences. Second, we present main aspects of the asymptotic theory related to time series regression models with many covariates. Third, we discuss various applications of statistical learning methodologies for time series analysis purposes.

Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-stationary data streams cause catastrophic forgetting of previously learned abilities. Rehearsal is a popular and effective way to mitigate this problem, which is storing past observations in a buffer and mixing them with new observations during learning. This leads to a question: Which stored samples should be selected for rehearsal? Choosing samples that are best for learning, rather than simply selecting them at random, could lead to significantly faster learning. For class incremental learning, prior work has shown that a simple class balanced random selection policy outperforms more sophisticated methods. Here, we revisit this question by exploring a new sample selection policy called GRASP. GRASP selects the most prototypical (class representative) samples first and then gradually selects less prototypical (harder) examples to update the DNN. GRASP has little additional compute or memory overhead compared to uniform selection, enabling it to scale to large datasets. We evaluate GRASP and other policies by conducting CL experiments on the large-scale ImageNet-1K and Places-LT image classification datasets. GRASP outperforms all other rehearsal policies. Beyond vision, we also demonstrate that GRASP is effective for CL on five text classification datasets.

These lecture notes are based on two series of lectures given by Andrea Montanari, first at the "Deep Learning Theory Summer School" at Princeton from July 27th to August 4th 2021, and then at the summer school "Statistical Physics & Machine Learning", that took place at Les Houches School of Physics in France from 4th to 29th July 2022. Theodor Misiakiewicz was Teaching Assistant to AM's lectures at the "Deep Learning Theory Summer School". We thank Boris Hanin for organizing the summer school in Princeton, and Florent Krzakala and Lenka Zdeborová from EPFL for organizing the summer school in Les Houches.

A general overview of current CP courses and instructional methods is presented, with a focus on online and virtually-delivered courses. This is followed by a discussion of the novel approach taken to introductory CP education for engineering students at large scale at the Georgia Institute of Technology (Georgia Tech) in Atlanta, GA, USA. The paper summarizes important takeaways from the Georgia Tech CP course and ends with a discussion on the future of CP education. Some ideas for instructional methods, promotional methods, and organizational changes are proposed to aid in the long-term growth of CP education.

Recently, Large Language Models (LLMs) have showcased remarkable capabilities in natural language understanding. While demonstrating proficiency in everyday conversations and question-answering situations, these models frequently struggle in domains that require precision, such as medical applications, due to their lack of domain-specific knowledge. In this paper, we describe the procedure for building a powerful, open-source language model specifically designed for medicine applications, termed as PMC-LLaMA. Our contributions are threefold: (i) we systematically investigate the process of adapting a general-purpose foundation language model towards medical domain, this involves data-centric knowledge injection through the integration of 4.8M biomedical academic papers and 30K medical textbooks, as well as comprehensive fine-tuning for alignment with domain-specific instructions; (ii) we contribute a large-scale, comprehensive dataset for instruction tuning. This dataset encompasses medical question-answering (QA), rationale for reasoning, and conversational dialogues, comprising a total of 202M tokens; (iii) we conduct thorough ablation studies to demonstrate the effectiveness of each proposed component. While evaluating on various public medical question-answering benchmarks, our lightweight PMCLLaMA, which consists of only 13 billion parameters, exhibits superior performance, even surpassing ChatGPT. All models, codes, datasets can be found in https://github.com/chaoyi-wu/PMC-LLaMA.

Federated learning (FL) has been introduced to the healthcare domain as a decentralized learning paradigm that allows multiple parties to train a model collaboratively without privacy leakage. However, most previous studies have assumed that every client holds an identical label set. In reality, medical specialists tend to annotate only diseases within their area of expertise or interest. This implies that label sets in each client can be different and even disjoint. In this paper, we propose the framework FedLSM to solve the problem of Label Set Mismatch. FedLSM adopts different training strategies on data with different uncertainty levels to efficiently utilize unlabeled or partially labeled data as well as class-wise adaptive aggregation in the classification layer to avoid inaccurate aggregation when clients have missing labels. We evaluated FedLSM on two public real-world medical image datasets, including chest X-ray (CXR) diagnosis with 112,120 CXR images and skin lesion diagnosis with 10,015 dermoscopy images, and showed that it significantly outperformed other state-of-the-art FL algorithms. The code can be found at https://github.com/dzp2095/FedLSM.