Physical Sciences and Mathematics Commons^™

A Dynamical Model Of Binding In Visual Cortex During Incremental Grouping And Search, Daniel Schmid, Daniel A. Braun, Heiko Neumann

MODVIS Workshop

Binding of visual information is crucial for several perceptual tasks. To incrementally group an object, elements in a space-feature neighborhood need to be bound together starting from an attended location (Roelfsema, TICS, 2005). To perform visual search, candidate locations and cued features must be evaluated conjunctively to retrieve a target (Treisman&Gormican, Psychol Rev, 1988). Despite different requirements on binding, both tasks are solved by the same neural substrate. In a model of perceptual decision-making, we give a mechanistic explanation for how this can be achieved. The architecture consists of a visual cortex module and a higher-order thalamic module. While the …

Wildfire Spread Prediction Using Attention Mechanisms In U-Net, Kamen Haresh Shah, Kamen Haresh Shah

Master's Theses

An investigation into using attention mechanisms for better feature extraction in wildfire spread prediction models. This research examines the U-net architecture to achieve image segmentation, a process that partitions images by classifying pixels into one of two classes. The deep learning models explored in this research integrate modern deep learning architectures, and techniques used to optimize them. The models are trained on 12 distinct observational variables derived from the Google Earth Engine catalog. Evaluation is conducted with accuracy, Dice coefficient score, ROC-AUC, and F1-score. This research concludes that when augmenting U-net with attention mechanisms, the attention component improves feature suppression …

Self-Supervised Video Object Segmentation Via Cutout Prediction And Tagging, Jyoti Kini, Fahad Shahbaz Khan, Salman Khan, Mubarak Shah

Computer Vision Faculty Publications

We propose a novel self-supervised Video Object Segmentation (VOS) approach that strives to achieve better object-background discriminability for accurate object segmentation. Distinct from previous self-supervised VOS methods, our approach is based on a discriminative learning loss formulation that takes into account both object and background information to ensure object-background discriminability, rather than using only object appearance. The discriminative learning loss comprises cutout-based reconstruction (cutout region represents part of a frame, whose pixels are replaced with some constant values) and tag prediction loss terms. The cutout-based reconstruction term utilizes a simple cutout scheme to learn the pixel-wise correspondence between the current …

Improving Reader Motivation With Machine Learning, Tanner A. Bohn

Electronic Thesis and Dissertation Repository

This thesis focuses on the problem of increasing reading motivation with machine learning (ML). The act of reading is central to modern human life, and there is much to be gained by improving the reading experience. For example, the internal reading motivation of students, especially their interest and enjoyment in reading, are important factors in their academic success.

There are many topics in natural language processing (NLP) which can be applied to improving the reading experience in terms of readability, comprehension, reading speed, motivation, etc. Such topics include personalized recommendation, headline optimization, text simplification, and many others. However, to the …

Generating Effective Sentence Representations: Deep Learning And Reinforcement Learning Approaches, Mahtab Ahmed

Electronic Thesis and Dissertation Repository

Natural language processing (NLP) is one of the most important technologies of the information age. Understanding complex language utterances is also a crucial part of artificial intelligence. Many Natural Language applications are powered by machine learning models performing a large variety of underlying tasks. Recently, deep learning approaches have obtained very high performance across many NLP tasks. In order to achieve this high level of performance, it is crucial for computers to have an appropriate representation of sentences. The tasks addressed in the thesis are best approached having shallow semantic representations. These representations are vectors that are then embedded in …

Impromptune: Symbolic Music Generation With Relative Attention Mechanisms, Connor J. Lennox

Honors Theses and Capstones

By combining attention-based mechanisms that have proved beneficial in the field of natural language processing with domain-specific knowledge about the structure of music, better predictions about piece continuations can be made. The goal of this work is to adapt current natural language processing techniques to a musical domain, and to generate new music by predicting continuations on a sequence of notes. An adaptation of traditional attention mechanisms to create a single prediction from sequential input is used to extend musical pieces by appending new elements repeatedly.

Is The Selective Tuning Model Of Visual Attention Still Relevant?, John K. Tsotsos

MODVIS Workshop

No abstract provided.

Speech Interfaces And Pilot Performance: A Meta-Analysis, Kenneth A. Ward

International Journal of Aviation, Aeronautics, and Aerospace

As the aviation industry modernizes, new technology and interfaces must support growing aircraft complexity without increasing pilot workload. Natural language processing presents just such a simple and intuitive interface, yet the performance implications for use by pilots remain unknown. A meta-analysis was conducted to understand performance effects of using speech and voice interfaces in a series of pilot task analogs. The inclusion criteria selected studies that involved participants performing a demanding primary task, such as driving, while interacting with a vehicle system to enter numbers, dial radios, or enter a navigation destination. Compared to manual system interfaces, voice interfaces reduced …

Focusing On Selection For Fixation, John K. Tsotsos, Calden Wloka, Yulia Kotseruba

MODVIS Workshop

Building on our presentation at MODVIS 2015, we continue in our quest to discover a functional, computational, explanation of the relationship among visual attention, interpretation of visual stimuli, and eye movements, and how these produce visual behavior. Here, we focus on one component, how selection is accomplished for the next fixation. The popularity of saliency map models drives the inference that this is solved; we suggested otherwise at MODVIS 2015. Here, we provide additional empirical and theoretical arguments. We then develop arguments that a cluster of complementary, conspicuity representations drive selection, modulated by task goals and history, leading to a …