The Development of Embodied Cognition: Six Lessons from Babies

By Linda B. Smith, Michael Gasser. 2005

688 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Developmental and Educational Psychology, Social Psychology, Natural Language Processing

How researchers see this paper

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

In Cognitive Neuroscience

In Developmental and Educational Psychology

In Social Psychology

In Natural Language Processing

Citations in the corpus

Experience Grounds Language (2020, background): “Language grounding enables an agent to connect words to these actionoriented categories for communication (Smith and Gasser, 2005), but requires action to fully discover”
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).”
Contrastive Multiview Coding (2019, background): “We revisit the classic hypothesis that the good bits are the ones that are shared between multiple views of the world, for example between multiple sensory modalities like vision, sound, and touch [70].”
MERLOT RESERVE: Neural Script Knowledge through Vision and Language and Sound (2022, background): “Reentry has been hypothesized by developmental psychologists to be crucial for how we as humans learn visual and world knowledge, much of it without need for an explicit teacher [88, 35, 19, 100].”
Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning (2017, neutral): “The idea of learning from paired audio-visual signals has been studied extensively in cognitive science (Smith and Gasser 2005), and early work introduced computational models for these ideas.”
A Survey of Embodied AI: From Simulators to Research Tasks (2021, background): “Embodied AI is the belief that true intelligence can emerge from the interactions of an agent with its environment [1].”
Learning to Poke by Poking: Experiential Learning of Intuitive Physics (2016, background): “This makes learning manipulation strategies without prior knowledge very challenging. spend years worth of time playing with objects in a seemingly random manner with no speciﬁc end goal (Smith & Gasser, 2005).”
Continual Learning for Robotics (2019, background): “This is generally done by a reward function that defines credit assignment Minsky (1961), or it can also be defined internally by more abstract rules such as self-supervision (Gopnik et al., 2001; Smith and Gasser, 2005), intrinsic motivation or curiosity (Oudeyer et al.”
Visual Reinforcement Learning with Imagined Goals (2018, background): “ors, and learning about the world around them. In fact, humans are very proﬁcient at setting abstract goals for themselves, and evidence shows that this behavior is already present from early infancy [43], albeit with simple goals such as reaching. The behavior and representation of goals grows more”
Habitat: A Platform for Embodied AI Research (2019, background): “ribution. 1. Introduction The embodiment hypothesis is the idea that intelligence emerges in the interaction of an agent with an environment and as a result of sensorimotor activity. Smith and Gasser [26] Imagine walking up to a home robot and asking ‘Hey – can you go check if my laptop is on my des”
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features (2018, background): “Misaligned sound [3×3×3 conv] × 4, 512 / [1,2,2]”
MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments (2017, background): “Multimodal perception is crucial for development of sensorimotor skills in animals (Smith and Gasser, 2005) and in artiﬁcial systems (Mirowski et al., 2017).”
Large-Scale Study of Curiosity-Driven Learning (2018, background): “Developmental psychologists talk about intrinsic motivation (i.e., curiosity) as the primary driver in the early stages of development [32, 41]: babies appear to employ goal-less exploration to learn skills that will be useful later on in life.”
Learning to Perform Physics Experiments via Deep Reinforcement Learning (2016, positive): “Inspired by developmental studies (Smith & Gasser, 2005), some recent works have focused on learning representations by predicting physical embodiment quantities such as ego-motion (Agrawal et al., 2015; Jayaraman & Grauman, 2015), instead of symbolic labels.”
Gibson Env: Real-World Perception for Embodied Agents (2018, background): “Apart from the application perspective, the findings supportive of a close relationship between visual perception and motion are prevalent on various fronts: evolutionary and computational biologists have hypothesized a key role for intermixing perception and locomotion in development of complex beh”
Generic 3D Representation via Pose Estimation and Matching (2016, background): “Cognitive studies suggest living organisms can perform cognitive tasks for which they have not received supervision by supervised learning of other foundational tasks [28,51,45].”
SIN: Semantic Inference Network for Few-Shot Streaming Label Learning (2022, background): “I N MANY real-world systems, relevant new concepts or labels gradually emerge with more in-depth exploration and understanding of data [1]–[3], [17]–[19].”