Timezone: »

Recursive Sketches for Modular Deep Learning
Badih Ghazi · Rina Panigrahy · Joshua R. Wang

Thu Jun 13 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #73

We present a mechanism to compute a sketch (succinct summary) of how a complex modular deep network processes its inputs. The sketch summarizes essential information about the inputs and outputs of the network and can be used to quickly identify key components and summary statistics of the inputs. Furthermore, the sketch is recursive and can be unrolled to identify sub-components of these components and so forth, capturing a potentially complicated DAG structure. These sketches erase gracefully; even if we erase a fraction of the sketch at random, the remainder still retains the high-weight'' information present in the original sketch. The sketches can also be organized in a repository to implicitly form aknowledge graph''; it is possible to quickly retrieve sketches in the repository that are related to a sketch of interest; arranged in this fashion, the sketches can also be used to learn emerging concepts by looking for new clusters in sketch space. Finally, in the scenario where we want to learn a ground truth deep network, we show that augmenting input/output pairs with these sketches can theoretically make it easier to do so.

Author Information

Badih Ghazi (Google)
Rina Panigrahy (Google)
Joshua R. Wang (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors