Search Results for author:
Found 24 papers, 2 papers with code
Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models
Large language models (LLMs) have performed well on several reasoning benchmarks, including ones that test analogical reasoning abilities.
Perspectives on the State and Future of Deep Learning -- 2023
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.
Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks
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.
The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain
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].
Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report
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.
Embodied, Situated, and Grounded Intelligence: Implications for AI
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.
The Debate Over Understanding in AI's Large Language Models
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.
Evaluating Understanding on Conceptual Abstraction Benchmarks
A long-held objective in AI is to build systems that understand concepts in a humanlike way.
Abstraction for Deep Reinforcement Learning
We characterise the problem of abstraction in the context of deep reinforcement learning.
Frontiers in Collective Intelligence: A Workshop Report
In August of 2021, the Santa Fe Institute hosted a workshop on collective intelligence as part of its Foundations of Intelligence project.
Frontiers in Evolutionary Computation: A Workshop Report
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.
Uncovering Universal Features: How Adversarial Training Improves Adversarial Transferability
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.
A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks
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.
Foundations of Intelligence in Natural and Artificial Systems: A Workshop Report
In March of 2021, the Santa Fe Institute hosted a workshop as part of its Foundations of Intelligence in Natural and Artificial Systems project.
Why AI is Harder Than We Think
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").
Abstraction and Analogy-Making in Artificial Intelligence
Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains.
Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers
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.
Next Wave Artificial Intelligence: Robust, Explainable, Adaptable, Ethical, and Accountable
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.
Revisiting Visual Grounding
We revisit a particular visual grounding method: the "Image Retrieval Using Scene Graphs" (IRSG) system of Johnson et al. (2015).
Semantic Image Retrieval via Active Grounding of Visual Situations
We describe a novel architecture for semantic image retrieval---in particular, retrieval of instances of visual situations.
Sparse Coding on Stereo Video for Object Detection
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.
Gaussian Processes with Context-Supported Priors for Active Object Localization
Next, we use a Gaussian Process to model this offset response signal over the search space of the target.
Fast On-Line Kernel Density Estimation for Active Object Localization
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.
Active Object Localization in Visual Situations
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.
