As a result, in the early pe-riod, people use deep learning as a tool to learn high level features from low level cues usually hand-crafted. Feb 2017 - IEEE Transactions on Image Processing M. Well then write a Python script that will use OpenCV and GoogleLeNet pre-trained on ImageNet to classify images. This course will introduce the fundamental technologies for autonomous vehicle sensors, perception and machine learning, from electromagnetic spectrum characteristics and signal acquisition, vehicle extrospective sensor data analysis, perspective geometry models, image and point cloud processing, to machinedeep learning approaches. Using Keras and Deep Deterministic Policy Gradient to play TORCS. Deep learning is an exciting, young field that specializes in discovering and extracting intricate structures in large, unstructured datasets for parameterizing artificial neural networks with many layers.