Building machines that learn and think with people

KM Collins, I Sucholutsky, U Bhatt, K Chandra… - Nature human …, 2024 - nature.com
What do we want from machine intelligence? We envision machines that are not just tools
for thought but partners in thought: reasonable, insightful, knowledgeable, reliable and …

Getting aligned on representational alignment

I Sucholutsky, L Muttenthaler, A Weller, A Peng… - arxiv preprint arxiv …, 2023 - arxiv.org
Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …

Improving neural network representations using human similarity judgments

L Muttenthaler, L Linhardt, J Dippel… - Advances in …, 2024 - proceedings.neurips.cc
Deep neural networks have reached human-level performance on many computer vision
tasks. However, the objectives used to train these networks enforce only that similar images …

Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning

F Mumuni, A Mumuni - Cognitive Systems Research, 2024 - Elsevier
We review current and emerging knowledge-informed and brain-inspired cognitive systems
for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or …

[HTML][HTML] Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models

BS Sankar, D Gilliland, J Rincon, H Hermjakob, Y Yan… - Bioengineering, 2024 - mdpi.com
Foundation Models (FMs) are gaining increasing attention in the biomedical artificial
intelligence (AI) ecosystem due to their ability to represent and contextualize multimodal …

How aligned are different alignment metrics?

J Ahlert, T Klein, F Wichmann, R Geirhos - arxiv preprint arxiv:2407.07530, 2024 - arxiv.org
In recent years, various methods and benchmarks have been proposed to empirically
evaluate the alignment of artificial neural networks to human neural and behavioral data. But …

Toward green and human-like artificial intelligence: A complete survey on contemporary few-shot learning approaches

G Tsoumplekas, V Li, V Argyriou, A Lytos… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite deep learning's widespread success, its data-hungry and computationally
expensive nature makes it impractical for many data-constrained real-world applications …

Human-in-the-loop mixup

KM Collins, U Bhatt, W Liu, V Piratla… - Uncertainty in …, 2023 - proceedings.mlr.press
Aligning model representations to humans has been found to improve robustness and
generalization. However, such methods often focus on standard observational data …

Quantum few-shot image classification

Z Huang, J Shi, X Li - IEEE Transactions on Cybernetics, 2024 - ieeexplore.ieee.org
Few-shot learning algorithms frequently exhibit suboptimal performance due to the limited
availability of labeled data. This article presents a novel quantum few-shot image …

What Matters to You? Towards Visual Representation Alignment for Robot Learning

R Tian, C Xu, M Tomizuka, J Malik, A Bajcsy - arxiv preprint arxiv …, 2023 - arxiv.org
When operating in service of people, robots need to optimize rewards aligned with end-user
preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards …