Downloads
Here are links from which you can download slides from our talks, and papers we’ve written. We’re always happy to answer questions, so please get in touch if you have any!
Conference proceedings: A neural network model of curiosity-driven infant categorization
Paper presented at the ICDL-EPIROB 2015, Brown University, Providence, RI, USA
Talk: Infants' exploration in a category learning task
Paper presented at the 2016 International Congress on Infant Studies, New Orleans, LA, USA
Poster: A neural network model of infants' curiosity-driven category learning
Poster presented at the 2015 launch of the ESRC International Centre for Language and Communicative Development launch
Poster: A Learned Label Modulates Object Representations in 10-Month-Old Infants
Poster presented at the 38th Annual Cognitive Science Society Meeting, Philadelphia, PA, USA
Talk: A Learned Label Modulates Object Representations in 10-Month-Old Infants
Paper presented at the 1st Lancaster Conference on Infant and Child Development, Lancaster, UK
Poster: How context affects early language acquisition: An embodied model of early referent selection and word learning
Poster presented at The Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics
Talk: The importance of nonlinguistic variability to early language learning: the case of colour
Poster presented at The Third ESRC International Centre for Language and Communicative Development (LuCiD) conderence, July 2017
Poster: Poster: New evidence for systematicity in infants’ curiosity-driven learning
Poster presented at the 2018 Budapest CEU Conference on Cognitive Development, Central European University, Budapest, Hungary. January, 2018.
Paper: Curiosity-based learning in infants: A neurocomputational approach
- We present a novel formalization of the mechanism underlying infants’ curiosity-driven learning during visual exploration.
- We implement this mechanism in a neural network that captures empirical data from an infant visual categorization task
- In the same model we test four potential curiosity mechanisms and show that learning is maximized when the model selects stimuli based on its learning history, its current plasticity and its learning environment
- The model offers new insight into how infants may drive their own learning
Lancaster University ©