constructions

The very early appearance of abstract knowledge is often taken as evidence for innateness. We explore the relative learning speeds of abstract and specific knowledge within a Bayesian framework, and the role for innate structure. We focus on knowledge about causality, seen as a domain-general intuitive theory, and ask whether this knowledge can be learned from cooccurrence of events. We begin by phrasing the causal Bayes nets theory of causality, and a range of alternatives, in a logical language for relational theories. This allows us to explore simultaneous inductive learning of an abstract theory of causality and a causal model for each of several causal systems. We find that the correct theory of causality can be learned relatively quickly, often becoming available before specific causal theories have been learned—an effect we term the blessing of abstraction. We then explore the effect of providing a variety of auxiliary evidence, and find that a collection of simple “perceptual input analyzers ” can help to bootstrap abstract knowledge. Together these results suggest that the most efficient route to causal knowledge may be to build in not an abstract notion of causality, but a powerful inductive learning mechanism and a variety of perceptual supports. While these results are purely computational, they have implications for cognitive development, which we explore in the conclusion. Pre-print June 2010—to appear in Psych. Review.

People can learn visual concepts from just one example, but it remains a mystery how this is accomplished. Many authors have proposed that transferred knowledge from more familiar concepts is a route to one shot learning, but what is the form of this abstract knowledge? One hypothesis is that the sharing of parts is core to one shot learning, and we evaluate this idea in the domain of handwritten characters, using a massive new dataset. These simple visual concepts have a rich internal part structure, yet they are particularly tractable for computational models. We introduce a generative model of how characters are composed from strokes, where knowledge from previous characters helps to infer the latent strokes in novel characters. The stroke model outperforms a competing stateof-the-art character model on a challenging one shot learning task, and it provides a good fit to human perceptual data.

This paper outlines a hierarchical Bayesian model for human category learning that learns both the organization of objects into categories, and the context in which this knowledge should be applied. The model is fit to multiple data sets, and provides a parsimonious method for describing how humans learn context specific conceptual representations. 1

We introduce HD (or “Hierarchical-Deep”) models, a new compositional learning architecture that integrates deep learning models with structured hierarchical Bayesian models. Specifically we show how we can learn a hierarchical Dirichlet process (HDP) prior over the activities of the top-level features in a Deep Boltzmann Machine (DBM). This compound HDP-DBM model learns to learn novel concepts from very few training examples, by learning low-level generic features, high-level features that capture correlations among low-level features, and a category hierarchy for sharing priors over the high-level features that are typical of different kinds of concepts. We present efficient learning and inference algorithms for the HDP-DBM model and show that it is able to learn new concepts from very few examples on CIFAR-100 object recognition, handwritten character recognition, and human motion capture datasets. 1

How is reinforcement learning possible in a high-dimensional world? Without making any assumptions about the structure of the state space, the amount of data required to effectively learn a value function grows exponentially with the state space’s dimensionality. However, humans learn to solve highdimensional problems much more rapidly than would be expected under this scenario. This suggests that humans employ inductive biases to guide (and accelerate) their learning. Here we propose one particular bias—sparsity—that ameliorates the computational challenges posed by high-dimensional state spaces, and present experimental evidence that humans can exploit sparsity information when it is available. Keywords: reinforcement learning; attention; Bayes.

Children learn causal relationships quickly, and make farreaching causal inferences on the basis of what they see. In knowledge to bear on their problems. This paper addresses children’s ability to acquire that knowledge. We present evidence that children can learn about the abstract properties of causal relationships using only a handful of events, and – consistent with a hierarchical Bayesian model of casual inference – children can be more sensitive to evidence than adults.

Learning to understand a single causal system can be an achievement, but humans must learn about multiple causal systems over the course of a lifetime. We present a hierarchical Bayesian framework that helps to explain how learning about several causal systems can accelerate learning about systems that are subsequently encountered. Given experience with a set of objects our framework learns a causal model for each object and a causal schema that captures commonalities among these causal models. The schema organizes the objects into categories and specifies the causal powers and characteristic features of these categories and the characteristic causal interactions between categories. A schema of this kind allows causal models for subsequent objects to be rapidly learned, and we explore this accelerated learning in four experiments. Our results confirm that humans learn rapidly about the causal powers of novel objects, and we show that our framework accounts better for our data than alternative models of causal learning.

Abstract not found

What is the value of an action that has never been tried before? One way to frame this question is as an inductive problem: how can I generalize my previous experience with one set of actions to a novel action? We show how hierarchical Bayesian inference can be used to solve this problem, and describe an equivalence between the Bayesian model and temporal difference learning algorithms that have been proposed as models of human reinforcement learning. In two experiments we test several predictions of this model, providing behavioral evidence that humans learn and exploit structured inductive knowledge to make predictions about novel actions. We suggest a new interpretation of dopaminergic responses to novelty in light of this model. Keywords: reinforcement learning, Bayesian inference, exploration, exploitation