Embedded Deep Learning: Algorithms, Architectures and Circuits for Always-on Neural Network Processing

Description

This book covers algorithmic and hardware implementation techniques to enable embedded deep learning. The authors describe synergetic design approaches on the application-, algorithmic-, computer architecture-, and circuit-level that will help in achieving the goal of reducing the computational cost of deep learning algorithms. The impact of these techniques is displayed in four silicon prototypes for embedded deep learning. Gives a wide overview of a series of effective solutions for energy-efficient neural networks on battery constrained wearable devices; Discusses the optimization of neural networks for embedded deployment on all levels of the design hierarchy – applications, algorithms, hardware architectures, and circuits – supported by real silicon prototypes; Elaborates on how to design efficient Convolutional Neural Network processors, exploiting parallelism and data-reuse, sparse operations, and low-precision computations; Supports the introduced theory and design concepts by four real silicon prototypes. The physical realization’s implementation and achieved performances are discussed elaborately to illustrated and highlight the introduced cross-layer design concepts. Front Matter ....Pages i-xvi Embedded Deep Neural Networks (Bert Moons, Daniel Bankman, Marian Verhelst)....Pages 1-31 Optimized Hierarchical Cascaded Processing (Bert Moons, Daniel Bankman, Marian Verhelst)....Pages 33-54 Hardware-Algorithm Co-optimizations (Bert Moons, Daniel Bankman, Marian Verhelst)....Pages 55-88 Circuit Techniques for Approximate Computing (Bert Moons, Daniel Bankman, Marian Verhelst)....Pages 89-113 ENVISION: Energy-Scalable Sparse Convolutional Neural Network Processing (Bert Moons, Daniel Bankman, Marian Verhelst)....Pages 115-151 BINAREYE: Digital and Mixed-Signal Always-On Binary Neural Network Processing (Bert Moons, Daniel Bankman, Marian Verhelst)....Pages 153-194 Conclusions, Contributions, and Future Work (Bert Moons, Daniel Bankman, Marian Verhelst)....Pages 195-200 Back Matter ....Pages 201-206