Forward pass for the conv2d layer

[milancurcic]

This PR implements:

• Forward pass for the conv2d layer
• layer % get_output method for the conv2d and input3d layers
• randn for 4-d data (used to initialize the convolution kernel)
• A few tests for the input3d layer
• Specific network % forward_3d method under the generic network % forward name

Some comments:

• In the current forward pass implementation, the following dimension ordering seems to be most efficient regarding the memory layout, e.g. for the convolution kernel: filters x channels x width x height. This is consistent with the channels-last convention used by TensorFlow: In the input data, channels (e.g. red, green, blue) vary the fastest, then image width, then image height.
• It looks like the convolution loop will provide some opportunity to parallelize (SPMD style)
• associate appears buggy with ifort-2021.5; avoid it (the associate construct; not the compiler) for the time being, and revisit and file bug reports once we have a working implementation (i.e. when Add support for convolutional layers #64 is closed).

TODO

• Make conv2d API consistent with the Keras API (i.e. conv2d(filters, kernel_size)).

Closes #60.

CC @katherbreen