The state-of-the-art online learning models generally conduct a single online gradient descent when a new sample arrives and thus suffer from suboptimal model weights. To this end, we introduce an online broad learning system framework with closed-form solutions for each online update. Different from employing existing incremental broad learning algorithms for online learning tasks, which tend to incur degraded accuracy and expensive online update overhead, we design an effective weight estimation algorithm and an efficient online updating strategy to remedy the above two deficiencies, respectively. Specifically, an effective weight estimation algorithm is first developed by replacing notorious matrix inverse operations with Cholesky decomposition and forward-backward substitution to improve model accuracy. Second, we devise an efficient online updating strategy that dramatically reduces online update time. Theoretical analysis exhibits the splendid error bound and low time complexity of our model. The most popular test-then-training evaluation experiments on various real-world datasets prove its superiority and efficiency. Furthermore, our framework is naturally extended to data stream scenarios with concept drift and exceeds state-of-the-art baselines.

This paper focuses on the piloting of the CGScholar AI Helper, a Generative AI (GenAI) assistant tool that aims to provide feedback on writing in high school contexts. The aim was to use GenAI to provide formative and summative feedback on students' texts in English Language Arts (ELA) and History. The trials discussed in this paper relate to Grade 11, a crucial learning phase when students are working towards college readiness. These trials took place in two very different schools in the Midwest of the United States, one in a low socio-economic background with low-performance outcomes and the other in a high socio-economic background with high-performance outcomes. The assistant tool used two main mechanisms "prompt engineering" based on participant teachers' assessment rubric and "fine-tuning" a Large Language Model (LLM) from a customized corpus of teaching materials using Retrieval Augmented Generation (RAG). This paper focuses on the CGScholar AI Helper's potential to enhance students' writing abilities and support teachers in ELA and other subject areas requiring written assignments.

This paper proposes an approach to optimally select samples for a small replay buffer to perform continual learning (CL) without forgetting. GEM/A-GEM) the problem is formulated from the perspective of constrained optimisation (minimise loss on current sample subject to loss not increasing on previous ones). Unlike GEM, with clear separation and knowledge of tasks, this approach addresses the general non-stationary learning problem. The paper proposes a theoretical argument for using the variance of gradients to select samples for the buffer. One related work that could also be cited is "Adapting Auxiliary Losses using Gradient Similarity", by Du et al, 2018 (https://arxiv.org/abs/1812.02224)

I'm not going to lie--when ChatGPT first came out and blew everyone's minds, I was pretty hesitant about it. I'm not going to say I was anti-AI, but I just figured I'd do the work myself to ensure it was right, especially since I'd heard a few of my coworkers complain about how ChatGPT could never give them perfect results. But in recent months, I've started getting so much more scrambled with work, and it's not super sustainable to rely on myself for all the answers. So, I finally started branching out and using ChatGPT, but ran into similar frustrations my coworkers did. Thankfully, I found this ChatGPT beginner course for only 9.99, and it's seriously upgraded how I understand the chatbot and create prompts.

Summary and Contributions: Update: My initial review noted two main issues with the paper: reliance on the initial model, and the use of task labels during the test phase. The author response addresses the first question, but misses the point on the second one. And this alone is not sufficient to strongly influence my overall rating. In my understanding, several previous methods, such as LwF, iCaRL highlighted in the author response, classify samples without the knowledge of which group of classes (i.e., old or new) they belong to. In other words, they only use a single framework that can identify samples from any of the old or the new classes, without additional information.

The paper proposes a continual learning approach for CNN models. This is achieved through spatial and channel-wise calibration modules, one for each new task. These calibration modules are introduced between each pair of consecutive layers in the original base model. The base model is learnt on the first task, and training data from the subsequent tasks is used to learn the calibration modules. Extensive experiments show the superiority of the proposed method in terms of accuracies, with minimal computation and storage overhead. It is important to emphasize that the proposed approach requires task labels in the test phase.

This work proposes algorithms for the online-within-online meta-learning setting as oppposed to the more prevalent statistical setting. In this particular meta-learning setting tasks arrive sequentially manner (outer loop) and then the learning per task itself happens in an online fashion. The aim is to have low average regret over tasks. The inner loop optimization is done via Online Mirror Descent (OMD). The inner algorithm design is carefully chosen to provide good approximations of (sub)-gradients of the outer meta objective.

This paper presents a method for online-within-online meta-learning where each task is revealed one after another and online learning is applied for within-task. The primal-dual online learning is the main ingredient. All of reviewers agree that the paper is well written and has valuable contributions, while a few relevant work is already available. During the discussion period, a reviewer with most negative review raised his/her score, enabling us to reach a consensus.

While this algorithm is specifically designed for detectors, Miech et al 2019 used unsupervised NCE losses (much like the ones in this paper) in order to understand the natural language descriptions associated with videos; the algorithm presented here seems like the most straightforward extension of this idea to bounding boxes. Little attention is given to demonstrating that the use of bounding boxes fundamentally changes the problem. Update The rebuttal addresses the following point regarding the accuracy of the evaluation. I had misunderstood the annotations that are available with epic kitchens, and therefore I am changing my review. I would encourage the authors to clarify the writing regarding what's available with epic kitchens.

This paper presents a method for learning a distribution of tasks to feed to an agent that's learning via meta RL, while simultaneously optimizing the agent to perform better more quickly on tasks sampled from this distribution. The task distribution is trained using an objective that maximizes mutual information between a latent task variable and the trajectories produced by the meta RL agent. The meta RL agent is trained to maximize this mutual information, more or less. The overall optimization relies on some variational lower bounds on mutual information, and on the RL 2 algorithm for meta RL. Experiments are provided which show that the task distributions and meta RL agents trained in this co-adaptive manner exhibit some potentially useful behaviors, e.g. an improved ability to quickly solve new tasks sampled from an "actual" task distribution -- i.e., a task distribution which is not equal to the one that's co-adapted with the agent.