Deep architectures are playing the most important role in the area of machine learning and are considered as the future technology and anticipated a complete paradigm shift in the area of artificial intelligent by the researchers. It is considered to be one of the most active areas of research in signal, image, vision, and biometrics and comprises of supervised and unsupervised models of approach for detection/ recognition/ classification/ synthesization of objects. With the advent of extraordinary computation power and huge data sets, it is possible to model the most complex processes using deep architectures. With the advent of Deep learning architectures, almost all areas of signal processing have undergone significant changes in their approach. This is primarily because machine learning is at the forefront of solving many problems in computer signal, image, vision and biometrics which were thought to be either unsolvable or highly computationally intensive in the past. One of the key ideas which have facilitated this is the introduction of deep architectures, which form the basis of present-day pattern-based recognition problems. The proposed Two-week course will be comprised of approximately 40 lectures followed by 14 hours worth of lab demonstration and hands-on approach is intended to help the participants familiarise themselves with Signal & Image Processing, Computer Vision, Biometrics and Machine Learning and pertains to how all of the approaches can be applied to research problems in real life. The course also covers essentials of machine learning, deep neural networks as well as the other models how they can be applied to solve practical problems in computer vision so that more people become interested in signal processing.