Building machines that learn and think with people
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 …
for thought but partners in thought: reasonable, insightful, knowledgeable, reliable and …
Getting aligned on representational alignment
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 …
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …
Improving neural network representations using human similarity judgments
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 …
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 …
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
Foundation Models (FMs) are gaining increasing attention in the biomedical artificial
intelligence (AI) ecosystem due to their ability to represent and contextualize multimodal …
intelligence (AI) ecosystem due to their ability to represent and contextualize multimodal …
How aligned are different alignment metrics?
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 …
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
Despite deep learning's widespread success, its data-hungry and computationally
expensive nature makes it impractical for many data-constrained real-world applications …
expensive nature makes it impractical for many data-constrained real-world applications …
Human-in-the-loop mixup
Aligning model representations to humans has been found to improve robustness and
generalization. However, such methods often focus on standard observational data …
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 …
availability of labeled data. This article presents a novel quantum few-shot image …
What Matters to You? Towards Visual Representation Alignment for Robot Learning
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 …
preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards …