Search Results - "Muttenthaler, Lukas"

Effective enhancement of attentional functions in the amblyopic brain by Muttenthaler, Lukas

“…This review endeavored to investigate whether patients who suffer from amblyopia show impairments in attentional functions and whether video games are…”
Get full text

THINGSvision: A Python Toolbox for Streamlining the Extraction of Activations From Deep Neural Networks by Muttenthaler, Lukas, Hebart, Martin N.

“…Over the past decade, deep neural network (DNN) models have received a lot of attention due to their near-human object classification performance and their…”
Get full text

Euler–Lagrange CFD simulation and experiments on accumulation and resuspension of particles in hydraulic reservoirs by Muttenthaler, Lukas, Manhartsgruber, Bernhard

“…Clean hydraulic oil is a major requirement for hydraulic systems. Hydraulic reservoirs are mostly considered as a storage of fluid but must fulfil more…”
Get full text

Corrigendum: A Novel Test of Pure Irrelevance-Induced Blindness by Büsel, Christian, Ditye, Thomas, Muttenthaler, Lukas, Ansorge, Ulrich

Get full text

A Novel Test of Pure Irrelevance-Induced Blindness by Büsel, Christian, Ditye, Thomas, Muttenthaler, Lukas, Ansorge, Ulrich

“…Load theory claims that bottom-up attention is possible under conditions of low perceptual load but not high perceptual load. At variance with this claim, a…”
Get full text

Interpretable object dimensions in deep neural networks and their similarities to human representations by Muttenthaler, Lukas, Hebart, Martin N.

Get full text

Assisted Declarative Process Creation from Natural Language Descriptions by Lopez, Hugo A., Marquard, Morten, Muttenthaler, Lukas, Stromsted, Rasmus

“…In this paper, we report recent advances on user support for declarative process generation from natural language descriptions. The Process Highlighter is a…”
Get full text

Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity by Muttenthaler, Lukas

“…Understanding subjectivity demands reasoning skills beyond the realm of common knowledge. It requires a machine learning model to process sentiment and to…”
Get full text

Dimensions underlying the representational alignment of deep neural networks with humans by Mahner, Florian P, Muttenthaler, Lukas, Güçlü, Umut, Hebart, Martin N

“…Determining the similarities and differences between humans and artificial intelligence is an important goal both in machine learning and cognitive…”
Get full text

Training objective drives the consistency of representational similarity across datasets by Ciernik, Laure, Linhardt, Lorenz, Morik, Marco, Dippel, Jonas, Kornblith, Simon, Muttenthaler, Lukas

“…The Platonic Representation Hypothesis claims that recent foundation models are converging to a shared representation space as a function of their downstream…”
Get full text

Unsupervised Evaluation for Question Answering with Transformers by Muttenthaler, Lukas, Augenstein, Isabelle, Bjerva, Johannes

“…It is challenging to automatically evaluate the answer of a QA model at inference time. Although many models provide confidence scores, and simple heuristics…”
Get full text

When Does Perceptual Alignment Benefit Vision Representations? by Sundaram, Shobhita, Fu, Stephanie, Muttenthaler, Lukas, Tamir, Netanel Y, Chai, Lucy, Kornblith, Simon, Darrell, Trevor, Isola, Phillip

“…Humans judge perceptual similarity according to diverse visual attributes, including scene layout, subject location, and camera pose. Existing vision models…”
Get full text

Human brain activity for machine attention by Muttenthaler, Lukas, Hollenstein, Nora, Barrett, Maria

“…Cognitively inspired NLP leverages human-derived data to teach machines about language processing mechanisms. Recently, neural networks have been augmented…”
Get full text

Set Learning for Accurate and Calibrated Models by Muttenthaler, Lukas, Vandermeulen, Robert A, Zhang, Qiuyi, Unterthiner, Thomas, Müller, Klaus-Robert

“…Model overconfidence and poor calibration are common in machine learning and difficult to account for when applying standard empirical risk minimization. In…”
Get full text

Improving neural network representations using human similarity judgments by Muttenthaler, Lukas, Linhardt, Lorenz, Dippel, Jonas, Vandermeulen, Robert A, Hermann, Katherine, Lampinen, Andrew K, Kornblith, Simon

“…Deep neural networks have reached human-level performance on many computer vision tasks. However, the objectives used to train these networks enforce only that…”
Get full text

Aligning Machine and Human Visual Representations across Abstraction Levels by Muttenthaler, Lukas, Greff, Klaus, Born, Frieda, Spitzer, Bernhard, Kornblith, Simon, Mozer, Michael C, Müller, Klaus-Robert, Unterthiner, Thomas, Lampinen, Andrew K

“…Deep neural networks have achieved success across a wide range of applications, including as models of human behavior in vision tasks. However, neural network…”
Get full text

Human alignment of neural network representations by Muttenthaler, Lukas, Dippel, Jonas, Linhardt, Lorenz, Vandermeulen, Robert A, Kornblith, Simon

“…Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and…”
Get full text

VICE: Variational Interpretable Concept Embeddings by Muttenthaler, Lukas, Zheng, Charles Y, McClure, Patrick, Vandermeulen, Robert A, Hebart, Martin N, Pereira, Francisco

“…A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces…”
Get full text

Getting aligned on representational alignment by Sucholutsky, Ilia, Muttenthaler, Lukas, Weller, Adrian, Peng, Andi, Bobu, Andreea, Kim, Been, Love, Bradley C, Grant, Erin, Groen, Iris, Achterberg, Jascha, Tenenbaum, Joshua B, Collins, Katherine M, Hermann, Katherine L, Oktar, Kerem, Greff, Klaus, Hebart, Martin N, Jacoby, Nori, Zhang, Qiuyi, Marjieh, Raja, Geirhos, Robert, Chen, Sherol, Kornblith, Simon, Rane, Sunayana, Konkle, Talia, O'Connell, Thomas P, Unterthiner, Thomas, Lampinen, Andrew K, Müller, Klaus-Robert, Toneva, Mariya, Griffiths, Thomas L

“…Biological and artificial information processing systems form representations that they can use to categorize, reason, plan, navigate, and make decisions. How…”
Get full text