no code implementations • 14 Feb 2024 • Martha Lewis, Melanie Mitchell
Large language models (LLMs) have performed well on several reasoning benchmarks, including ones that test analogical reasoning abilities.
no code implementations • 7 Dec 2023 • Micah Goldblum, Anima Anandkumar, Richard Baraniuk, Tom Goldstein, Kyunghyun Cho, Zachary C Lipton, Melanie Mitchell, Preetum Nakkiran, Max Welling, Andrew Gordon Wilson
The goal of this series is to chronicle opinions and issues in the field of machine learning as they stand today and as they change over time.
no code implementations • 14 Nov 2023 • Melanie Mitchell, Alessandro B. Palmarini, Arseny Moskvichev
We explore the abstract reasoning abilities of text-only and multimodal versions of GPT-4, using the ConceptARC benchmark [10], which is designed to evaluate robust understanding and reasoning with core-knowledge concepts.
1 code implementation • 11 May 2023 • Arseny Moskvichev, Victor Vikram Odouard, Melanie Mitchell
In this paper we describe an in-depth evaluation benchmark for the Abstraction and Reasoning Corpus (ARC), a collection of few-shot abstraction and analogy problems developed by Chollet [2019].
no code implementations • 27 Oct 2022 • Michael L. Littman, Ifeoma Ajunwa, Guy Berger, Craig Boutilier, Morgan Currie, Finale Doshi-Velez, Gillian Hadfield, Michael C. Horowitz, Charles Isbell, Hiroaki Kitano, Karen Levy, Terah Lyons, Melanie Mitchell, Julie Shah, Steven Sloman, Shannon Vallor, Toby Walsh
In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society.
no code implementations • 24 Oct 2022 • Tyler Millhouse, Melanie Moses, Melanie Mitchell
In April of 2022, the Santa Fe Institute hosted a workshop on embodied, situated, and grounded intelligence as part of the Institute's Foundations of Intelligence project.
no code implementations • 14 Oct 2022 • Melanie Mitchell, David C. Krakauer
We survey a current, heated debate in the AI research community on whether large pre-trained language models can be said to "understand" language -- and the physical and social situations language encodes -- in any important sense.
no code implementations • 28 Jun 2022 • Victor Vikram Odouard, Melanie Mitchell
A long-held objective in AI is to build systems that understand concepts in a humanlike way.
no code implementations • 10 Feb 2022 • Murray Shanahan, Melanie Mitchell
We characterise the problem of abstraction in the context of deep reinforcement learning.
no code implementations • 13 Dec 2021 • Tyler Millhouse, Melanie Moses, Melanie Mitchell
In August of 2021, the Santa Fe Institute hosted a workshop on collective intelligence as part of its Foundations of Intelligence project.
no code implementations • 20 Oct 2021 • Tyler Millhouse, Melanie Moses, Melanie Mitchell
In July of 2021, the Santa Fe Institute hosted a workshop on evolutionary computation as part of its Foundations of Intelligence in Natural and Artificial Systems project.
no code implementations • ICML Workshop AML 2021 • Jacob M. Springer, Melanie Mitchell, Garrett T. Kenyon
Adversarial examples for neural networks are known to be transferable: examples optimized to be misclassified by a “source” network are often misclassified by other “destination” networks.
no code implementations • NeurIPS 2021 • Jacob M. Springer, Melanie Mitchell, Garrett T. Kenyon
Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source classifier are often misclassified as well by classifiers with different architectures.
no code implementations • 5 May 2021 • Tyler Millhouse, Melanie Moses, Melanie Mitchell
In March of 2021, the Santa Fe Institute hosted a workshop as part of its Foundations of Intelligence in Natural and Artificial Systems project.
1 code implementation • 26 Apr 2021 • Melanie Mitchell
Since its beginning in the 1950s, the field of artificial intelligence has cycled several times between periods of optimistic predictions and massive investment ("AI spring") and periods of disappointment, loss of confidence, and reduced funding ("AI winter").
no code implementations • 22 Feb 2021 • Melanie Mitchell
Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains.
no code implementations • 9 Feb 2021 • Jacob M. Springer, Melanie Mitchell, Garrett T. Kenyon
The results we present in this paper provide new insight into the nature of the non-robust features responsible for adversarial vulnerability of neural network classifiers.
no code implementations • 11 Dec 2020 • Odest Chadwicke Jenkins, Daniel Lopresti, Melanie Mitchell
In the most recent wave research in AI has largely focused on deep (i. e., many-layered) neural networks, which are loosely inspired by the brain and trained by "deep learning" methods.
no code implementations • WS 2019 • Erik Conser, Kennedy Hahn, Chandler M. Watson, Melanie Mitchell
We revisit a particular visual grounding method: the "Image Retrieval Using Scene Graphs" (IRSG) system of Johnson et al. (2015).
no code implementations • 31 Oct 2017 • Max H. Quinn, Erik Conser, Jordan M. Witte, Melanie Mitchell
We describe a novel architecture for semantic image retrieval---in particular, retrieval of instances of visual situations.
no code implementations • 19 May 2017 • Sheng Y. Lundquist, Melanie Mitchell, Garrett T. Kenyon
We show that replacing a typical supervised convolutional layer with an unsupervised sparse-coding layer within a DCNN allows for better performance on a car detection task when only a limited number of labeled training examples is available.
no code implementations • 25 Mar 2017 • Anthony D. Rhodes, Jordan Witte, Melanie Mitchell, Bruno Jedynak
Next, we use a Gaussian Process to model this offset response signal over the search space of the target.
no code implementations • 16 Nov 2016 • Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell
In our system, prior situation knowledge is captured by a set of flexible, kernel-based density estimations---a situation model---that represent the expected spatial structure of the given situation.
no code implementations • 2 Jul 2016 • Max H. Quinn, Anthony D. Rhodes, Melanie Mitchell
We compare the results with several baselines and variations on our method, and demonstrate the strong benefit of using situation knowledge and active context-driven localization.