Search Results for author:
Found 39 papers, 20 papers with code
Neural networks that overcome classic challenges through practice
Since the earliest proposals for neural network models of the mind and brain, critics have pointed out key weaknesses in these models compared to human cognitive abilities.
H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark
In this work, we obtain a more robust estimate of human performance by evaluating 1729 humans on the full set of 400 training and 400 evaluation tasks from the original ARC problem set.
Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
We present a case study of a fundamental, yet surprisingly difficult, relational reasoning task: judging whether two visual entities are the same or different.
Goals as Reward-Producing Programs
People are remarkably capable of generating their own goals, beginning with child's play and continuing into adulthood.
Compositional learning of functions in humans and machines
Extending the investigation into the visual domain, we developed a function learning paradigm to explore the capacity of humans and neural network models in learning and reasoning with compositional functions under varied interaction conditions.
A systematic investigation of learnability from single child linguistic input
However, a significant gap exists between the training data for these models and the linguistic input a child receives.
Self-supervised learning of video representations from a child's perspective
These results suggest that important temporal aspects of a child's internal model of the world may be learnable from their visual experience using highly generic learning algorithms and without strong inductive biases.
Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations
Much of this prior work focuses on training convolutional neural networks to classify images of two same or two different abstract shapes, testing generalization on within-distribution stimuli.
Compositional diversity in visual concept learning
In few shot classification tasks, we find that people and the program induction model can make a range of meaningful compositional generalizations, with the model providing a strong account of the experimental data as well as interpretable parameters that reveal human assumptions about the factors invariant to category membership (here, to rotation and changing part attachment).
Learning high-level visual representations from a child's perspective without strong inductive biases
Young children develop sophisticated internal models of the world based on their visual experience.
A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines
In this work, we re-examine the inductive biases of neural networks by adapting the stimuli and procedure from Geirhos et al. (2019) to more closely follow the developmental paradigm and test on a wide range of pre-trained neural networks.
Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning
Human reasoning can often be understood as an interplay between two systems: the intuitive and associative ("System 1") and the deliberative and logical ("System 2").
Flexible Compositional Learning of Structured Visual Concepts
Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples.
Fast and flexible: Human program induction in abstract reasoning tasks
The Abstraction and Reasoning Corpus (ARC) is a challenging program induction dataset that was recently proposed by Chollet (2019).
Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
To achieve human-like common sense about everyday life, machine learning systems must understand and reason about the goals, preferences, and actions of other agents in the environment.
Word meaning in minds and machines
Machines have achieved a broad and growing set of linguistic competencies, thanks to recent progress in Natural Language Processing (NLP).
Self-supervised learning through the eyes of a child
Within months of birth, children develop meaningful expectations about the world around them.
Learning Task-General Representations with Generative Neuro-Symbolic Modeling
We develop a generative neuro-symbolic (GNS) model of handwritten character concepts that uses the control flow of a probabilistic program, coupled with symbolic stroke primitives and a symbolic image renderer, to represent the causal and compositional processes by which characters are formed.
Generating new concepts with hybrid neuro-symbolic models
A second tradition has emphasized statistical knowledge, viewing conceptual knowledge as an emerging from the rich correlational structure captured by training neural networks and other statistical models.
Learning Compositional Rules via Neural Program Synthesis
Many aspects of human reasoning, including language, require learning rules from very little data.
Learning word-referent mappings and concepts from raw inputs
How do children learn correspondences between the language and the world from noisy, ambiguous, naturalistic input?
A Benchmark for Systematic Generalization in Grounded Language Understanding
In this paper, we introduce a new benchmark, gSCAN, for evaluating compositional generalization in situated language understanding.
Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning
We explore the benefits of augmenting state-of-the-art model-free deep reinforcement algorithms with simple object representations.
Modeling question asking using neural program generation
People ask questions that are far richer, more informative, and more creative than current AI systems.
Mutual exclusivity as a challenge for deep neural networks
Strong inductive biases allow children to learn in fast and adaptable ways.
Improving the robustness of ImageNet classifiers using elements of human visual cognition
As reported in previous work, we show that an explicit episodic memory improves the robustness of image recognition models against small-norm adversarial perturbations under some threat models.
Compositional generalization through meta sequence-to-sequence learning
People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket."
People infer recursive visual concepts from just a few examples
Machine learning has made major advances in categorizing objects in images, yet the best algorithms miss important aspects of how people learn and think about categories.
Learning a smooth kernel regularizer for convolutional neural networks
We propose a smooth kernel regularizer that encourages spatial correlations in convolution kernel weights.
The Omniglot challenge: a 3-year progress report
Three years ago, we released the Omniglot dataset for one-shot learning, along with five challenge tasks and a computational model that addresses these tasks.
Human few-shot learning of compositional instructions
There have been striking recent improvements in machine learning for natural language processing, yet the best algorithms require vast amounts of experience and struggle to generalize new concepts in compositional ways.
Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks
Systematic compositionality is the ability to recombine meaningful units with regular and predictable outcomes, and it's seen as key to humans' capacity for generalization in language.
Learning Inductive Biases with Simple Neural Networks
People use rich prior knowledge about the world in order to efficiently learn new concepts.
Question Asking as Program Generation
A hallmark of human intelligence is the ability to ask rich, creative, and revealing questions.
Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks
Humans can understand and produce new utterances effortlessly, thanks to their compositional skills.
The Emergence of Organizing Structure in Conceptual Representation
While this approach can learn intuitive organizations, including a tree for animals and a ring for the color circle, it assumes a strong inductive bias that considers only these particular forms, and each form is explicitly provided as initial knowledge.
Building Machines That Learn and Think Like People
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people.
Softstar: Heuristic-Guided Probabilistic Inference
Recent machine learning methods for sequential behavior prediction estimate the motives of behavior rather than the behavior itself.
One-shot learning by inverting a compositional causal process
People can learn a new visual class from just one example, yet machine learning algorithms typically require hundreds or thousands of examples to tackle the same problems.
