David Marr

"To understand the relationship between behavior and brain one has to begin by defining the function, or computational goal, of a complete behavior. Only then can a neuroscientist determine how the brain achieves that goal."

"Vision is a process that produces from images of the external world a description that is useful to the viewer and not cluttered with irrelevant information."

"A representation is a formal system for making explicit certain entities or types of information, together with a specification of how the system does this. And I shall call the result of using a representation to describe a given entity a description of the entity in that representation."

"The critical act in formulating computational theories turns out to be the discovery of valid constraints on the way the world is structured -- constraints that provide sufficient information to allow the processing to succeed."

"The primitives of a representation are the most elementary units of shape information available in a representation."

"Vision is the process of discovering from images what is present in the world, and where it is."

"The abstract properties of this mapping are defined precisely, and its appropriateness and adequacy for the task at hand are demonstrated."

"In order to understand bird flight, we have to understand aerodynamics; only then does the structure of feathers and the different shapes of bird's wings make sense."

"[If] we can experimentally isolate a process and show that it can still work well, then it cannot require complex interaction with other parts of vision and can therefore be understood relatively well on its own."

"When David Marr at MIT moved into computer vision, he generated a lot of excitement, but he hit up against the problem of knowledge representation; he had no good representations for knowledge in his vision systems."

"I am not sure that Marr would agree, but I am tempted to add learning as the very top level of understanding, above the computational level. [...] Only then may we be able to build intelligent machines that could learn to see—and think—without the need to be programmed to do it."