Overview of the Neural Network Compression and Representation (NNR) Standard
Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks. The NNR standard contains quantization and an arithmetic coding scheme as core encoding and decoding technologies, as...
ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
In this chapter, we develop and describe a novel quantization paradigm for DNNs: Our method leverages concepts of explainable AI (XAI) and concepts of information theory: Instead of assigning weight values based on their distances to the...
Explaining the Predictions of Unsupervised Learning Models
In this chapter, we review our recently proposed "neuralization-propagation" (NEON) approach for bringing XAI to workhorses of unsupervised learning. NEON first converts the unsupervised model into a functionally equivalent neural network so...
xxAI - Beyond Explainable AI
This book takes next steps towards a broader vision for explainable AI in moving beyond explaining classifiers, to include explaining other kinds of models (e.g., unsupervised and reinforcement learning models) via a diverse array of XAI...
Hybrid Polymer THz Receiver PIC with Waveguide Integrated Photoconductive Antenna: Concept and 1st Characterization Results
An all-photonic THz-receiver PIC comprising an on-chip frequency stabilization scheme and a novel InP-based photoconductive antenna is presented in this paper. Characterization of the key photonic building blocks shows the functionality of the...
A new concept for spatially resolved coherent detection with vertically illuminated photodetectors targeting ranging applications
This paper proposes a novel approach for coherent detection with double-side vertically illuminated photodetectors. Signal and local oscillator are injected collinearly from opposite sides of the photodetector chip. The concept inherently...
Coherent Detection With Double-Side Vertically Illuminated Photodiodes for Spatially Resolved Ranging Applications
We theoretically investigate and demonstrate coherent detection with double-side vertically illuminated photodiodes by injecting signal and local oscillator collinearly from opposite sides of the photodetector chip. A first proof of concept for...
Characterization, Monitoring, and Mitigation of Standard C-Band Transceivers I/Q Imbalance in Multiband Systems
To keep up with the rapid growth in global traffic, next-generation optical communication networks aim to vastly increase capacity by exploiting a larger optical transmission window covering the S-C-L-band. To reuse current commercially available...
Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation
We present a solution for Accurate and temporally consistent modeling of human performances from video sequences. In detail, we derive parameters of a sequence of body models, representing shape and motion of a person, including jaw poses, facial...