Magnus Johnsson

Cognitive Scientist, Computer Scientist







Referee Assignments


Action Recognition




I am a cognitive scientist and a computer scientist. My research interests are wide and include computational modeling, computational intelligence, artificial neural networks, artificial intelligence, computational cognitive neuroscience, cognitive robotics, and the philosophy of mind. I try to understand how natural cognitive systems (brains) work from a system theoretic and computational perspective by computational modelling, but also how to create artificial cognitive mechanisms. This provides methods and applications to solve practical problems (e.g. medical diagnosis and forecasting), but could also be more complete artificial cognitive architectures (artificial brains) at some level. I'm also curious about and try to understand more about consciousness and qualia.

I do research on Artificial Neural Networks (ANNs) and other kinds of machine learning, and I have invented some novel variants of the Self-Organizing Map (SOM). One of these, the Associative Self-Organizing Map (A-SOM), can learn to associate its self-organized representation of its input with something external, for example the activity in another A-SOM or its own activity at an earlier time. This enables cross-modal expectations (e.g. after a lightning you expect thunder), and internal simulation, i.e. the idea proposed by Germund Hesslow that when we imagine that we perceive something or do something (mental imagery), we actually activate the same brain areas in similar ways as if we actually had the perception or acted in the way we imagined. ANNs are very much employed in my cognitive models, but I'm also interested in ANN based applications and other applications, e.g. medical diagnosis and data mining.

Recently, I have done research on how the abilities of humans and other creatures to recognize actions and understand the intentions of others are implemented in the brain, and in particular how similar abilities could be implemented artificially in systems for action recognition.

I'm very interested in modelling in general for all kinds of applications, in the industry, in medicine, in finance etc. For example I have been involved in simulating the re-organization of the somatosensory cortex after injuries to the nerves between the hand and the brain, and in modelling urological dysfunction. I have also done much work on bio-inspired haptic (tactile) perception in robots, and I have designed and built some (now outdated) robots for this aim.