Related papers: Analyzing machine-learned representations: A natur…
Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few examples, and combining these rules to form compositional rule-based…
An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: what are…
Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that…
Although large language models (LLMs) have demonstrated remarkable proficiency in modeling text and generating human-like text, they may exhibit biases acquired from training data in doing so. Specifically, LLMs may be susceptible to a…
We compare the acquisition of knowledge in humans and machines. Research from the field of developmental psychology indicates, that human-employed hypothesis are initially guided by simple rules, before evolving into more complex theories.…
Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to…
Advances in deep learning systems have allowed large models to match or surpass human accuracy on a number of skills such as image classification, basic programming, and standardized test taking. As the performance of the most capable…
Human communication is increasingly intermixed with language generated by AI. Across chat, email, and social media, AI systems suggest words, complete sentences, or produce entire conversations. AI-generated language is often not identified…
Natural language provides a widely accessible and expressive interface for robotic agents. To understand language in complex environments, agents must reason about the full range of language inputs and their correspondence to the world.…
Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalization has been limited.…
Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good…
What do artificial neural networks (ANNs) learn? The machine learning (ML) community shares the narrative that ANNs must develop abstract human concepts to perform complex tasks. Some go even further and believe that these concepts are…
Understanding how people behave in strategic settings--where they make decisions based on their expectations about the behavior of others--is a long-standing problem in the behavioral sciences. We conduct the largest study to date of…
With the advent of large labelled datasets and high-capacity models, the performance of machine vision systems has been improving rapidly. However, the technology has still major limitations, starting from the fact that different vision…
The perceptual representations supporting our ability to recognize faces remain a computational mystery. Deep neural networks offer mechanistic hypotheses for human face perception, but theoretically distinct models often make…
Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distribution densely. We study a common setting where our task is not…
The human cognitive system exhibits remarkable flexibility and generalization capabilities, partly due to its ability to form low-dimensional, compositional representations of the environment. In contrast, standard neural network…
A machine learning system can score well on a given test set by relying on heuristics that are effective for frequent example types but break down in more challenging cases. We study this issue within natural language inference (NLI), the…
The mouse is one of the most studied animal models in the field of systems neuroscience. Understanding the generalized patterns and decoding the neural representations that are evoked by the diverse range of natural scene stimuli in the…
In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…