At present, machines implement narrow artificial intelligence which performs one specific task in a single domain, such as facial recognition, personalised recommendations, driving a car, etc. These systems additionally have limitations such as failure to adapt to new scenarios, dependency on huge curated training datasets, and losing past knowledge when learning new information. Going beyond such barriers, the goal is to create general intelligent systems which possesses human-like cognitive skills: having the common sense to conduct a broad range of tasks, learning new things without compromising old knowledge, and adapting to a new environment to achieve goals.

Studying cognition in children and their learning mechanisms might be the key to achieving the desired traits above. One instance of this is
reflected in children’s word-learning mechanisms: children quickly map words and the concept being represented, strengthening the associations with increasing exposures.

Therefore, this work is an artistic approach towards visualising said associative learning, aiming to highlight the potential of infant learning as a pathway to general intelligence in machines. 

Just as a child develops an understanding of the world from the information present around it, the bot tries to make sense of itself and its environment as it ‘crawls’ on the web.