The first RECOD hands-on deep learning workshop took place on last April 16-17. The workshop was open to all RECODists (students and researchers) and the goal was to take a very practical approach over the basic models of deep learning. Starting from scratch and exploring how the theory maps onto concrete commands, the main frameworks were explored: Theano, Torch7 and Caffe. The RECOD cluster provided the infrastructure, which counts with several GPUs and Condor/Docker to manage the running experiments. At RECOD, Deep Learning is quickly becoming a staple of our research, a tendency we hope the workshop will intensify. Enjoy some photos taken during the weekend.