In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on past data. Our work demonstrates a limitation of this approach: networks trained with experience replay tend to have unstable optimization trajectories, impeding their overall accuracy. Surprisingly, these instabilities persist even when the replay buffer stores all previous training examples, suggesting that this issue is orthogonal to catastrophic forgetting. We minimize these instabilities through a simple modification of the optimization geometry. Our solution, Layerwise Proximal Replay (LPR), balances learning from new and replay data while only allowing for gradual changes in the hidden activation of past data. We demonstrate that LPR consistently improves replay-based online continual learning methods across multiple problem settings, regardless of the amount of available replay memory.

Incremental learning (IL) is essential to realize the human-level intelligence in the neural network. However, existing IL scenarios and datasets are unqualified for assessing forgetting in PLMs, giving an illusion that PLMs do not suffer from catastrophic forgetting. To this end, we propose a challenging IL scenario called instance-incremental learning (IIL) and a novel dataset called Concept-1K, which supports an order of magnitude larger IL steps. Based on the experiments on Concept-1K, we reveal that billion-parameter PLMs still suffer from catastrophic forgetting, and the forgetting is affected by both model scale, pretraining, and buffer size. Furthermore, existing IL methods and a popular finetuning technique, LoRA, fail to achieve satisfactory performance. Our study provides a novel scenario for future studies to explore the catastrophic forgetting of PLMs and encourage more powerful techniques to be designed for alleviating the forgetting in PLMs. The data, code and scripts are publicly available at https://github.com/zzz47zzz/pretrained-lm-for-incremental-learning.

The wide availability of specific courses together with the flexibility of academic plans in university studies reveal the importance of Recommendation Systems (RSs) in this area. These systems appear as tools that help students to choose courses that suit to their personal interests and their academic performance. This paper presents a hybrid RS that combines Collaborative Filtering (CF) and Content-based Filtering (CBF) using multiple criteria related both to student and course information to recommend the most suitable courses to the students. A Genetic Algorithm (GA) has been developed to automatically discover the optimal RS configuration which include both the most relevant criteria and the configuration of the rest of parameters. The experimental study has used real information of Computer Science Degree of University of Cordoba (Spain) including information gathered from students during three academic years, counting on 2500 entries of 95 students and 63 courses. Experimental results show a study of the most relevant criteria for the course recommendation, the importance of using a hybrid model that combines both student information and course information to increase the reliability of the recommendations as well as an excellent performance compared to previous models.

The knowledge concept recommendation in Massive Open Online Courses (MOOCs) is a significant issue that has garnered widespread attention. Existing methods primarily rely on the explicit relations between users and knowledge concepts on the MOOC platforms for recommendation. However, there are numerous implicit relations (e.g., shared interests or same knowledge levels between users) generated within the users' learning activities on the MOOC platforms. Existing methods fail to consider these implicit relations, and these relations themselves are difficult to learn and represent, causing poor performance in knowledge concept recommendation and an inability to meet users' personalized needs. To address this issue, we propose a novel framework based on contrastive learning, which can represent and balance the explicit and implicit relations for knowledge concept recommendation in MOOCs (CL-KCRec). Specifically, we first construct a MOOCs heterogeneous information network (HIN) by modeling the data from the MOOC platforms. Then, we utilize a relation-updated graph convolutional network and stacked multi-channel graph neural network to represent the explicit and implicit relations in the HIN, respectively. Considering that the quantity of explicit relations is relatively fewer compared to implicit relations in MOOCs, we propose a contrastive learning with prototypical graph to enhance the representations of both relations to capture their fruitful inherent relational knowledge, which can guide the propagation of students' preferences within the HIN. Based on these enhanced representations, to ensure the balanced contribution of both towards the final recommendation, we propose a dual-head attention mechanism for balanced fusion. Experimental results demonstrate that CL-KCRec outperforms several state-of-the-art baselines on real-world datasets in terms of HR, NDCG and MRR.

This research aims to explore the impact of Machine Learning (ML) on the evolution and efficacy of Recommendation Systems (RS), particularly in the context of their growing significance in commercial business environments. Methodologically, the study delves into the role of ML in crafting and refining these systems, focusing on aspects such as data sourcing, feature engineering, and the importance of evaluation metrics, thereby highlighting the iterative nature of enhancing recommendation algorithms. The deployment of Recommendation Engines (RE), driven by advanced algorithms and data analytics, is explored across various domains, showcasing their significant impact on user experience and decision-making processes. These engines not only streamline information discovery and enhance collaboration but also accelerate knowledge acquisition, proving vital in navigating the digital landscape for businesses. They contribute significantly to sales, revenue, and the competitive edge of enterprises by offering improved recommendations that align with individual customer needs. The research identifies the increasing expectation of users for a seamless, intuitive online experience, where content is personalized and dynamically adapted to changing preferences. Future research directions include exploring advancements in deep learning models, ethical considerations in the deployment of RS, and addressing scalability challenges. This study emphasizes the indispensability of comprehending and leveraging ML in RS for researchers and practitioners, to tap into the full potential of personalized recommendation in commercial business prospects.

The advent of Generative AI (GenAI) in education presents a transformative approach to traditional teaching methodologies, which often overlook the diverse needs of individual students. This study introduces a GenAI tool, based on advanced natural language processing, designed as a digital assistant for educators, enabling the creation of customized lesson plans. The tool utilizes an innovative feature termed 'interactive mega-prompt,' a comprehensive query system that allows educators to input detailed classroom specifics such as student demographics, learning objectives, and preferred teaching styles. This input is then processed by the GenAI to generate tailored lesson plans. To evaluate the tool's effectiveness, a comprehensive methodology incorporating both quantitative (i.e., % of time savings) and qualitative (i.e., user satisfaction) criteria was implemented, spanning various subjects and educational levels, with continuous feedback collected from educators through a structured evaluation form. Preliminary results show that educators find the GenAI-generated lesson plans effective, significantly reducing lesson planning time and enhancing the learning experience by accommodating diverse student needs. This AI-driven approach signifies a paradigm shift in education, suggesting its potential applicability in broader educational contexts, including special education needs (SEN), where individualized attention and specific learning aids are paramount

Artificial intelligence (AI) advances and the rapid adoption of generative AI tools like ChatGPT present new opportunities and challenges for higher education. While substantial literature discusses AI in higher education, there is a lack of a systemic approach that captures a holistic view of the AI transformation of higher education institutions (HEIs). To fill this gap, this article, taking a complex systems approach, develops a causal loop diagram (CLD) to map the causal feedback mechanisms of AI transformation in a typical HEI. Our model accounts for the forces that drive the AI transformation and the consequences of the AI transformation on value creation in a typical HEI. The article identifies and analyzes several reinforcing and balancing feedback loops, showing how, motivated by AI technology advances, the HEI invests in AI to improve student learning, research, and administration. The HEI must take measures to deal with academic integrity problems and adapt to changes in available jobs due to AI, emphasizing AI-complementary skills for its students. However, HEIs face a competitive threat and several policy traps that may lead to decline. HEI leaders need to become systems thinkers to manage the complexity of the AI transformation and benefit from the AI feedback loops while avoiding the associated pitfalls. We also discuss long-term scenarios, the notion of HEIs influencing the direction of AI, and directions for future research on AI transformation.

Scripted agents have predominantly won the five previous iterations of the IEEE microRTS (µRTS) competitions hosted at CIG and CoG. Despite Deep Reinforcement Learning (DRL) algorithms making significant strides in real-time strategy (RTS) games, their adoption in this primarily academic competition has been limited due to the considerable training resources required and the complexity inherent in creating and debugging such agents. In a benchmark without performance constraints, RAISocketAI regularly defeated the two prior competition winners. This first competition-winning DRL submission can be a benchmark for future microRTS competitions and a starting point for future DRL research. Iteratively fine-tuning the base policy and transfer learning to specific maps were critical to RAISocketAI's winning performance. These strategies can be used to economically train future DRL agents. Further work in Imitation Learning using Behavior Cloning and fine-tuning these models with DRL has proven promising as an efficient way to bootstrap models with demonstrated, competitive behaviors. Deep reinforcement learning (DRL) has proven to be powerful at solving complex problems requiring several steps to achieve a goal, such as Atari games (Mnih et al., 2013), continuous control tasks (Lillicrap et al., 2016), and even real-time strategy (RTS) games like StarCraft II (Vinyals et al., 2019). The StarCraft II grandmaster agent AlphaStar was trained with thousands of CPUs and GPUs/TPUs for several weeks. RTS games are particularly challenging for DRL for several reasons: (1) the observation and action spaces are large and varied with different terrain and unit types; (2) each unit type can have different actions and abilities; (3) each action can control several units at once; (4) rewards are sparse (win, loss, or tie) and delayed by possibly several thousand timesteps; (5) winning requires combining tactical (micro) and strategic (macro) decisions; (6) actions must be taken in real-time (i.e., the game won't wait for the agent to take an action); (7) the agent might not have full visibility of the game state (i.e., fog of war); and (8) events in the game might be non-deterministic. It includes many aspects of RTS games, simplified: different unit types, unit-specific actions, terrain, resource collection and utilization to build units, and unit-to-unit combat where units have different strengths and weaknesses. The IEEE microRTS competitions have been hosted at the Conference on Games (CoG) nearly every year since 2019 and at the Conference on Computational Intelligence and Games (CIG) before that since 2017 (Ontañón et al., 2018).

Generative AI is changing the way that many disciplines are taught, including computer science. Researchers have shown that generative AI tools are capable of solving programming problems, writing extensive blocks of code, and explaining complex code in simple terms. Particular promise has been shown in using generative AI to enhance programming error messages. Both students and instructors have complained for decades that these messages are often cryptic and difficult to understand. Yet recent work has shown that students make fewer repeated errors when enhanced via GPT-4. We extend this work by implementing feedback from ChatGPT for all programs submitted to our automated assessment tool, Athene, providing help for compiler, run-time, and logic errors. Our results indicate that adding generative AI to an automated assessment tool does not necessarily make it better and that design of the interface matters greatly to the usability of the feedback that GPT-4 provided.

Recently text-to-image models have gained widespread attention in the community due to their controllable and high-quality generation ability. However, the robustness of such models and their potential ethical issues have not been fully explored. In this paper, we introduce Universal Semantic Trigger, a meaningless token sequence that can be added at any location within the input text yet can induce generated images towards a preset semantic target.To thoroughly investigate it, we propose Semantic Gradient-based Search (SGS) framework. SGS automatically discovers the potential universal semantic triggers based on the given semantic targets. Furthermore, we design evaluation metrics to comprehensively evaluate semantic shift of images caused by these triggers. And our empirical analyses reveal that the mainstream open-source text-to-image models are vulnerable to our triggers, which could pose significant ethical threats. Our work contributes to a further understanding of text-to-image synthesis and helps users to automatically auditing their models before deployment.