Core knowledge.

By Elizabeth S. Spelke, Katherine D. Kinzler. 2007

1,512 citations recorded by the source corpus.

Subfields: Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Science & Psychology

Citations in the corpus

Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions (2017, background): “Understanding the exact form of the priors is an active, very challenging, area of research (Spelke & Kinzler, 2007; Smith & Gasser, 2005).”
What can the brain teach us about building artificial intelligence? (2016, background): “Early in development, humans have a foundational understanding of several core domains (Spelke, 2003; Spelke & Kinzler, 2007).”
CLEVRER: CoLlision Events for Video REpresentation and Reasoning (2019, background): “The ability to recognize objects and reason about their behaviors in physical events from videos lies at the core of human cognitive development (Spelke, 2000).”
Unsupervised Learning of Object Keypoints for Perception and Control (2019, background): “On the other hand, humans explicitly learn notions of objects, relations, geometry and cardinality in a task-agnostic manner [31] and re-purpose this knowledge to future tasks.”
Relational inductive biases, deep learning, and graph networks (2018, background): “…which guide these approaches towards learning about entities and relations (Mitchell, 1980), which we, joining many others (Spelke et al., 1992; Spelke and Kinzler, 2007; Marcus, 2001; Tenenbaum et al., 2011; Lake et al., 2017; Lake and Baroni, 2018; Marcus, 2018b), suggest are an essential…”
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions (2018, background): “Common-sense physical reasoning is facilitated by the discovery and representation of objects (a core domain of human cognition (Spelke & Kinzler, 2007)) that serve as primitives of a compositional system.”
Visual Interaction Networks: Learning a Physics Simulator from Video (2017, background): “Physical reasoning is a core domain of human knowledge [21] and among the earliest topics in AI [23, 24].”
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation (2016, methodology): “There is converging evidence in developmental psychology that human infants, primates, children, and adults in diverse cultures base their core knowledge on certain cognitive systems including – entities, agents and their actions, numerical quantities, space, social-structures and intuitive theories”
Learning to Learn for Global Optimization of Black Box Functions (2016, background): “Findings in developmental psychology have revealed that infants are endowed with a small number of separable systems of core knowledge for reasoning about objects, actions, number, space, and possibly social interactions [Spelke and Kinzler, 2007].”
Graph networks as learnable physics engines for inference and control (2018, background): “Cognitive scientists have long pointed to rich generative models as central to perception, reasoning, and decision-making (Craik, 1967; Johnson-Laird, 1980; Miall & Wolpert, 1996; Spelke & Kinzler, 2007; Battaglia et al., 2013).”
A Survey of Reinforcement Learning Informed by Natural Language (2019, background): “Humans are able to learn quickly in new environments due to a rich set of commonsense priors about the world [Spelke and Kinzler, 2007], some of which are reflected in natural language [Shusterman et al.”
Recurrent Relational Networks (2017, background): “A central component of human intelligence is the ability to abstractly reason about objects and their interactions [Spelke et al., 1995, Spelke and Kinzler, 2007].”
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning (2018, background): “In particular, the perceptual grouping of the world into objects and their relations constitutes core knowledge in cognition (Spelke & Kinzler, 2007).”
Learning Object Affordances: From Sensory--Motor Coordination to Imitation (2008, background): “As newborns, the robot should " start " with a minimal subset of core (phylogenetic) capabilities [20] to bootstrap learning mechanisms that, through self-experimentation and interaction with the environment and other humans, would progressively lead to the acquisition of new skills.”
Neural Bases of Cognitive Development (2007, background): “A number of distinguished cognitive developmentalists and cognitive theorists have proposed or at least implied that elements of number concept (Wynn, 1992; Wynn, Bloom, & Chiang, 2002), object permanence (Baillargeon, 1987; Baillargeon, Spelke, & Wasserman, 1985; Spelke, 2000), and perhaps face rec”