Gradient check speedups

[jeffdonahue]

Two changes to the gradient checker that improve performance pretty significantly without any cost to unit test coverage.

(1) 8901fe7 moves the analytic gradient computation outside the loop over bottom features and stores it throughout all finite differencing computation (extra storage should be pretty minimal since the unit tests use relatively tiny blobs).

(2) 061b0db adds a method GradientCheckEltwise that replaces GradientCheckExhaustive in many layers. In any layer where we have element-wise computation where each output is a function only of the input at the corresponding index (e.g., neuron layers), we only need to do finite-differencing to compute the diagonal of the jacobian and we know all other entries are zero.

In my tests of the entire unit test suite (./build/test/test_all.testbin on a k40) this gave a 73% speedup from 238,610 ms @ dev down to 66,322 ms.

[shelhamer]

Testing in a minute is sweet! Now all I have to do is bring up the build bot and our tests will be perpetual.

Thanks Jeff!