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.
A method for collecting human supervision that combines rules and instance labels.
S4 learns new self-supervision automatically, improving accuracy with less human effort.
Proposes PA-DSL for correcting noisy human labels in automated data labeling.
Survey on making machine learning models more understandable.
Programmatic Motion Concepts learn human actions from paired videos.
In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples wit…
In this study, importance of user inputs is studied in the context of personalizing human activity recognition models using incremental learning. Inertial sensor data from three body positions are used, and the classification is based on Learn++ ensemble method. Three different approaches to update models are compared:…
AutoML frameworks outperform human data scientists on 7 out of 12 OpenML tasks.
A promising approach for teaching artificial agents to use natural language involves using human-in-the-loop training. However, recent work suggests that current machine learning methods are too data inefficient to be trained in this way from scratch. In this paper, we investigate the relationship between two categorie…
Automates galaxy morphology classification with less human labelling.
Relation extraction aims to extract relational facts from sentences. Previous models mainly rely on manually labeled datasets, seed instances or human-crafted patterns, and distant supervision. However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision sa…
LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
Bayesian algorithms improve crowdsourcing with label and instance constraints.
Humans navigate complex environments in an organized yet flexible manner, adapting to the context and implicit social rules. Understanding these naturally learned patterns of behavior is essential for applications such as autonomous vehicles. However, algorithmically defining these implicit rules of human behavior rema…
Optimizes classifiers for varying levels of automation.
Enhances AI models with human feedback for noisy data.
This paper demonstrates the use of genetic algorithms for evolving a grandmaster-level evaluation function for a chess program. This is achieved by combining supervised and unsupervised learning. In the supervised learning phase the organisms are evolved to mimic the behavior of human grandmasters, and in the unsupervi…
Semi-automatic data annotation helps experts label unlabeled samples based on feature space projection.
Speaker diarization, which is to find the speech segments of specific speakers, has been widely used in human-centered applications such as video conferences or human-computer interaction systems. In this paper, we propose a self-supervised audio-video synchronization learning method to address the problem of speaker d…
Improved NTL detection using human-in-the-loop approach with explainability.
Plud system reduces labeling time and produces accurate models for uncategorized images.
XGL uses global explanations to guide human supervision in machine learning.
The latent spaces of GAN models often have semantically meaningful directions. Moving in these directions corresponds to human-interpretable image transformations, such as zooming or recoloring, enabling a more controllable generation process. However, the discovery of such directions is currently performed in a superv…
LCBM model improves image classification without human supervision.
A method for trust evaluation of devices in human-device coexistence systems.
SPIN converts weak LLMs to strong ones using self-play.
In this study, we propose a novel deep neural network and its supervised learning method that uses a feedforward supervisory signal. The method is inspired by the human visual system and performs human-like association-based learning without any backward error propagation. The feedforward supervisory signal that produc…
Human trafficking is among the most challenging law enforcement problems which demands persistent fight against from all over the globe. In this study, we leverage readily available data from the website "Backpage"-- used for classified advertisement-- to discern potential patterns of human trafficking activities which…
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on multimodal unsupervised learning (as infants) and active learning (as children). Wit…
Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled examples with unlabeled examples, often resulting in improved performance. Howe…
Deep Reinforcement Learning (DRL) algorithms are known to be data inefficient. One reason is that a DRL agent learns both the feature and the policy tabula rasa. Integrating prior knowledge into DRL algorithms is one way to improve learning efficiency since it helps to build helpful representations. In this work, we co…
Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning. Recently, concerns about the viability of learning disentangled representations in a purely unsupervised manner has spurred a shift toward the incorporat…
Using supervised machine learning approaches to recognize human activities from on-body wearable accelerometers generally requires a large amount of labelled data. When ground truth information is not available, too expensive, time consuming or difficult to collect, one has to rely on unsupervised approaches. This pape…
Geometric framework detects concept frustration between human concepts and machine representations.
Semi-supervised clustering seeks to augment traditional clustering methods by incorporating side information provided via human expertise in order to increase the semantic meaningfulness of the resulting clusters. However, most current methods are \emph{passive} in the sense that the side information is provided before…
Self-play fine-tuning improves diffusion models for text-to-image generation.
Unified framework for human motion generation on Riemannian manifolds.
New method pools labels from similar data items to improve learning from small samples.
LISBET automates social behavior analysis using machine learning.
Improved speech enhancement with larger neural networks using novel embeddings and biases.
Today's densely instrumented world offers tremendous opportunities for continuous acquisition and analysis of multimodal sensor data providing temporal characterization of an individual's behaviors. Is it possible to efficiently couple such rich sensor data with predictive modeling techniques to provide contextual, and…
Paper proposes semi-supervised learning using change points for sequence classification.
AlphaZero reveals new chess concepts learnable by top experts.
CPATTA uses conformal prediction for efficient test-time adaptation.
Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering. However, it is impractical to ask human oracles to answer every query correctly. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose an effective algorithm …
ADPO optimizes relative advantage in reinforcement learning from human feedback.
Paper tackles active learning under human label variation, proposing a new framework.
AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing