Estimating the difficulty of exam questions is essential for developing good exams, but professors are not always good at this task. We compare various Large Language Model-based methods with three professors in their ability to estimate what percentage of students will give correct answers on True/False exam questions in the areas of Neural Networks and Machine Learning. Our results show that the professors have limited ability to distinguish between easy and difficult questions and that they are outperformed by directly asking Gemini 2.5 to solve this task. Yet, we obtained even better results using uncertainties of the LLMs solving the questions in a supervised learning setting, using only 42 training samples. We conclude that supervised learning using LLM uncertainty can help professors better estimate the difficulty of exam questions, improving the quality of assessment.

Keywords-recommendation system; machine learning; Non-groups based on their viewing patterns. Agent Recurrent Deterministic Policy Gradient (MA-RDPG) The proliferation of digital content has necessitated the algorithm, as suggested by Zhao et al., this research aims to development of effective recommendation systems to aid users optimize overall system performance through enhanced in navigating vast amounts of data. This research aims to explore and implement advanced machine Previous studies have extensively explored collaborative learning techniques [1-6] to create a high-performing movie filtering techniques for recommendation systems. The study addresses the following (2001) [13] demonstrated the effectiveness of matrix research questions: What are the most effective machine factorization in uncovering latent user-item interactions. How do et al. (2009) [14] further refined these techniques, leading to these models compare in terms of accuracy and relevance?

By enrolling in this course you agree to the End User License Agreement as set out in the FAQ. This course, Advanced Machine Learning and Signal Processing, is part of the IBM Advanced Data Science Specialization which IBM is currently creating and gives you easy access to the invaluable insights into Supervised and Unsupervised Machine Learning Models used by experts in many field relevant disciplines. We'll learn about the fundamentals of Linear Algebra to understand how machine learning modes work. Then we introduce the most popular Machine Learning Frameworks for python Scikit-Learn and SparkML. SparkML is making up the greatest portion of this course since scalability is key to address performance bottlenecks.

Abstract: This work explores an efficient approach to establish a foundational video-text model for tasks including open-vocabulary video classification, text-to-video retrieval, video captioning and video question-answering. We present VideoCoCa that reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules (for example, cross-frame attention layer or perceiver resampler) and finetune the modified architecture on video-text data, we surprisingly find that the generative attentional pooling and contrastive attentional pooling layers in the image-text CoCa design are instantly adaptable to flattened frame embeddings'', yielding a strong zero-shot transfer baseline for many video-text tasks. Specifically, the frozen image encoder of a pretrained image-text CoCa takes each video frame as inputs and generates N token embeddings per frame for totally T video frames. We flatten N T token embeddings as a long sequence of frozen video representation and apply CoCa's generative attentional pooling and contrastive attentional pooling on top. All model weights including pooling layers are directly loaded from an image-text CoCa pretrained model.

Abstract: Zero-shot cross-lingual named entity recognition (NER) aims at transferring knowledge from annotated and rich-resource data in source languages to unlabeled and lean-resource data in target languages. Existing mainstream methods based on the teacher-student distillation framework ignore the rich and complementary information lying in the intermediate layers of pre-trained language models, and domain-invariant information is easily lost during transfer. In this study, a mixture of short-channel distillers (MSD) method is proposed to fully interact the rich hierarchical information in the teacher model and to transfer knowledge to the student model sufficiently and efficiently. Concretely, a multi-channel distillation framework is designed for sufficient information transfer by aggregating multiple distillers as a mixture. Besides, an unsupervised method adopting parallel domain adaptation is proposed to shorten the channels between the teacher and student models to preserve domain-invariant features.

Abstract: Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies. While highly general, their learning dynamics are often times heuristic and inflexible -- exactly the limitations that meta-learning can address. Hence, we propose to discover effective update rules for evolution strategies via meta-learning. Concretely, our approach employs a search strategy parametrized by a self-attention-based architecture, which guarantees the update rule is invariant to the ordering of the candidate solutions. We show that meta-evolving this system on a small set of representative low-dimensional analytic optimization problems is sufficient to discover new evolution strategies capable of generalizing to unseen optimization problems, population sizes and optimization horizons. Furthermore, the same learned evolution strategy can outperform established neuroevolution baselines on supervised and continuous control tasks.

Abstract: Poisson log-linear models are ubiquitous in many applications, and one of the most popular approaches for parametric count regression. In the Bayesian context, however, there are no sufficient specific computational tools for efficient sampling from the posterior distribution of parameters, and standard algorithms, such as random walk Metropolis-Hastings or Hamiltonian Monte Carlo algorithms, are typically used. Herein, we developed an efficient Metropolis-Hastings algorithm and importance sampler to simulate from the posterior distribution of the parameters of Poisson log-linear models under conditional Gaussian priors with superior performance with respect to the state-of-the-art alternatives. The key for both algorithms is the introduction of a proposal density based on a Gaussian approximation of the posterior distribution of parameters. Via simulation, we obtained that the time per independent sample of the proposed samplers is competitive with that obtained using the successful Hamiltonian Monte Carlo sampling, with the Metropolis-Hastings showing superior performance in all scenarios considered.

Abstract: The use of machine learning methods helps to improve decision making in different fields. In particular, the idea of bridging predictions (machine learning models) and prescriptions (optimization problems) is gaining attention within the scientific community. One of the main ideas to address this trade-off is the so-called Constraint Learning (CL) methodology, where the structures of the machine learning model can be treated as a set of constraints to be embedded within the optimization problem, establishing the relationship between a direct decision variable x and a response variable y. However, most CL approaches have focused on making point predictions for a certain variable, not taking into account the statistical and external uncertainty faced in the modeling process. In this paper, we extend the CL methodology to deal with uncertainty in the response variable y. The novel Distributional Constraint Learning (DCL) methodology makes use of a piece-wise linearizable neural network-based model to estimate the parameters of the conditional distribution of y (dependent on decisions x and contextual information), which can be embedded within mixed-integer optimization problems.

Abstract: Contrastive Learning has recently achieved state-of-the-art performance in a wide range of tasks. Many contrastive learning approaches use mined hard negatives to make batches more informative during training but these approaches are inefficient as they increase epoch length proportional to the number of mined negatives and require frequent updates of nearest neighbor indices or mining from recent batches. In this work, we provide an alternative to hard negative mining in supervised contrastive learning, Tail Batch Sampling (TBS), an efficient approximation to the batch assignment problem that upper bounds the gap between the global and training losses, LGlobal LTrain. TBS \textbf{improves state-of-the-art performance} in sentence embedding ( 0.37 Spearman) and code-search tasks ( 2.2\% MRR), is easy to implement -- requiring only a few additional lines of code, does not maintain external data structures such as nearest neighbor indices, is more computationally efficient when compared to the most minimal hard negative mining approaches, and makes no changes to the model being trained. Abstract: Collaborative filtering (CF) models easily suffer from popularity bias, which makes recommendation deviate from users' actual preferences.

Abstract: Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can provide accurate annotations. However, the performance of the semantic segmentation model trained with the data of the simulator will significantly decrease when applied in the actual scene. Unsupervised domain adaptation (UDA) for semantic segmentation has recently gained increasing research attention, aiming to reduce the domain gap and improve the performance on the target domain.