Deep Neural Networks: A Signal Processing Perspective
Tutkimustuotos › › vertaisarvioitu
|Otsikko||Handbook of Signal Processing Systems|
|DOI - pysyväislinkit|
|Tila||Julkaistu - 2019|
|OKM-julkaisutyyppi||A3 Kirjan tai muun kokoomateoksen osa|
Deep learning has rapidly become the state of the art in machine learning, surpassing traditional approaches by a significant margin for many widely studied benchmark sets. Although the basic structure of a deep neural network is very close to a traditional 1990s style network, a few novel components enable successful training of extremely deep networks, thus allowing a completely novel sphere of applications—often reaching human-level accuracy and beyond. Below, we familiarize the reader with the brief history of deep learning and discuss the most significant milestones over the years. We also describe the fundamental components of a modern deep neural networks and emphasize their close connection to the basic operations of signal processing, such as the convolution and the Fast Fourier Transform. We study the importance of pretraining with examples and, finally, we will discuss the real time deployment of a deep network; a topic often dismissed in textbooks; but increasingly important in future applications, such as self driving cars.