A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Bayesian model identifies skill difficulties and student subgroups in engineering education.
Generative Adversarial Networks (GANs) have a great performance in image generation, but they need a large scale of data to train the entire framework, and often result in nonsensical results. We propose a new method referring to conditional GAN, which equipments the latent noise with mixture of Student's t-distributio…
The increasingly fast development cycle for online course contents, along with the diverse student demographics in each online classroom, make real-time student outcomes prediction an interesting topic for both industrial research and practical needs. In this paper, we tackle the problem of real-time student performanc…
Self-distillation improves model performance by increasing teacher diversity and smoothing predictions.
Increasingly fast development and update cycle of online course contents, and diverse demographics of students in each online classroom, make student performance prediction in real-time (before the course finishes) and/or on curriculum without specific historical performance data available interesting topics for both i…
Enhances student diversity in collaborative learning.
TAdam optimizes machine learning models to resist noise effectively.
Tailoring the presentation of information to the needs of individual students leads to massive gains in student outcomes~\cite{bloom19842}. This finding is likely due to the fact that different students learn differently, perhaps as a result of variation in ability, interest or other factors~\cite{schiefele1992interest…
A new method for student-initiated action advice using novelty detection.
KT models improved slightly with synthetic student data.
Understanding large-scale patterns in student course enrollment is a problem of great interest to university administrators and educational researchers. Yet important decisions are often made without a good quantitative framework of the process underlying student choices. We propose a probabilistic approach to modellin…
Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-for…
Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate pr…
An important, yet largely unstudied, problem in student data analysis is to detect misconceptions from students' responses to open-response questions. Misconception detection enables instructors to deliver more targeted feedback on the misconceptions exhibited by many students in their class, thus improving the quality…
Estimates model performance from compute budget for distillation.
Study shows GDP and CPI predict CCC funding, highlighting need for economic forecasting.
The study uses Hidden Markov Models to analyze student enrollment patterns and academic performance.
Inspired by the unsupervised learning or self-organization in the machine learning context, here we attempt to draw `learning curve' for the collective behavior of job-seeking `zero-intelligence' labors in successive job-hunting processes. Our labor market is supposed to be opened especially for university graduates in…
Deep convolutional neural networks have been widely used in numerous applications, but their demanding storage and computational resource requirements prevent their applications on mobile devices. Knowledge distillation aims to optimize a portable student network by taking the knowledge from a well-trained heavy teache…
Study shows how task similarity affects forgetting in teacher-student setup.
Study shows financial literacy, social capital, and financial tech positively impact financial inclusion of Indonesian students.
We consider the machine teaching problem in a classroom-like setting wherein the teacher has to deliver the same examples to a diverse group of students. Their diversity stems from differences in their initial internal states as well as their learning rates. We prove that a teacher with full knowledge about the learnin…
More accurate machine learning models often demand more computation and memory at test time, making them difficult to deploy on CPU- or memory-constrained devices. Teacher-student compression (TSC), also known as distillation, alleviates this burden by training a less expensive student model to mimic the expensive teac…
Deep learning based knowledge tracing model has been shown to outperform traditional knowledge tracing model without the need for human-engineered features, yet its parameters and representations have long been criticized for not being explainable. In this paper, we propose Deep-IRT which is a synthesis of the item res…
Study shows human advisors use context to improve student outcomes in algorithm-assisted advising.
This note presents an operational measure of fat-tailedness for univariate probability distributions, in where 0 is maximally thin-tailed (Gaussian) and 1 is maximally fat-tailed. Among others,1) it helps assess the sample size needed to establish a comparative needed for statistical significance, 2) allows…
AutoStan improves Bayesian models via predictive feedback.
Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is little knowledge of the resulting cost-benefit. We propose structural model distillation for memory reduction using a strategy that produces a …
Lecture note for data science students on machine learning basics and advanced topics.
The development of real-time affect detection models often depends upon obtaining annotated data for supervised learning by employing human experts to label the student data. One open question in annotating affective data for affect detection is whether the labelers (i.e., human experts) need to be socio-culturally sim…
Study finds flipped classrooms improve student self-concept, enjoyment, but not exam scores.
New diffusion models capture heavy-tailed distributions better.
For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise. On top of that, we apply a logits select…
Electronic health records (EHR) systems contain vast amounts of medical information about patients. These data can be used to train machine learning models that can predict health status, as well as to help prevent future diseases or disabilities. However, getting patients' medical data to obtain well-trained machine l…
The main objective of exams consists in performing an assessment of students' expertise on a specific subject. Such expertise, also referred to as skill or knowledge level, can then be leveraged in different ways (e.g., to assign a grade to the students, to understand whether a student might need some support, etc.). S…
In this paper, we present a deep neural network (DNN) training approach called the "DeepMimic" training method. Enormous amounts of data are available nowadays for training usage. Yet, only a tiny portion of these data is manually labeled, whereas almost all of the data are unlabeled. The training approach presented ut…
Method transfers feature representation from large to small models using perception coherence.
Paper introduces active and passive causal inference techniques.
Purveyors of malicious network attacks continue to increase the complexity and the sophistication of their techniques, and their ability to evade detection continues to improve as well. Hence, intrusion detection systems must also evolve to meet these increasingly challenging threats. Machine learning is often used to …
Enhances model compression with multi-teacher knowledge distillation.
In this article we present pictorially the foundation of differential geometry which is a crucial tool for multiple areas of physics, notably general and special relativity, but also mechanics, thermodynamics and solving differential equations. As all the concepts are presented as pictures, there are no equations in th…
Vision algorithms capable of interpreting scenes from a real-time video stream are necessary for computer-assisted surgery systems to achieve context-aware behavior. In laparoscopic procedures one particular algorithm needed for such systems is the identification of surgical phases, for which the current state of the a…
The holy grail in deep neural network research is porting the memory- and computation-intensive network models on embedded platforms with a minimal compromise in model accuracy. To this end, we propose a novel approach, termed as Variational Student, where we reap the benefits of compressibility of the knowledge distil…
Recent advances in deep learning have facilitated the demand of neural models for real applications. In practice, these applications often need to be deployed with limited resources while keeping high accuracy. This paper touches the core of neural models in NLP, word embeddings, and presents a new embedding distillati…
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments. To do so, we study how a teacher algorithm can learn to generate a learning curriculum, whereby it sequentially samples parameters contr…
As an automatic method of determining model complexity using the training data alone, Bayesian linear regression provides us a principled way to select hyperparameters. But one often needs approximation inference if distribution assumption is beyond Gaussian distribution. In this paper, we propose a Bayesian linear reg…
This is an elementary introduction to a method for studying harmonic maps into symmetric spaces, and in particular for studying constant mean curvature (CMC) surfaces, that was developed by J. Dorfmeister, F. Pedit and H. Wu. There already exist a number of other introductions to this method, but all of them require a …
This paper offers a mathematical introduction to GANs.