Deep learning is a huge topic today; speeding up the computation with convolutional neural network is crucial for fast classification. In this work we show how fine-tuned canonical polyadic (CP) decomposition can be used to speedup CNN by a factor of 8-10.
| 26/05/2016 | A TT-eigenvalue solver that finally works | Papers |
| 12/05/2016 | Exponential machines and tensor trains | Papers |
| 06/04/2016 | Convergence analysis of a projected fixed-point iteration | Papers |
| 30/03/2016 | Compress-and-eliminate solver for sparse matrices | Papers |
| 01/12/2015 | New paper in SIMAX | Papers |
We are located at the 2-nd floor of the new "Technopark-3” building in Skolkovo (few kilometers outside Moscow Ring Road). The building is accessible from Skolkovo Road (Сколковское шоссе) and Minskoe Highway (Минское шоссе).
email: 