D&R Industry Articles

Featured Article

Pyramid Vector Quantization and Bit Level Sparsity in Weights for Efficient Neural Networks Inference

This paper discusses three basic blocks for the inference of convolutional neural networks (CNNs). Pyramid Vector Quantization (PVQ) is discussed as an effective quantizer for CNNs weights resulting in highly sparse and compressible networks. Properties of PVQ are exploited for the elimination of multipliers during inference while maintaining high performance. The result is then extended to any other quantized weights. The Tiny Yolo v3 CNN is used to compare such basic blocks.

Featured Article

Enabling Bluetooth Out-of-Band pairing through NFC

Many services offered over Bluetooth can expose private data or let a connecting party control the Bluetooth device. Security reasons make it necessary to recognize specific devices, and thus enable control over which devices can connect to a given Bluetooth device.

Featured Article

Towards Self-Driving Cars: MIPI D-PHY Enabling Advanced Automotive Applications

Since the invention of the automobile well over a century ago, car manufacturers have been focused on creating the highest-speed, safest, and most fuel-efficient cars possible.

Featured Article

Designing AI enabled System with SOTIF (Safety Of The Intended Functionality)

Autonomous Vehicles (AV) needs more intelligence when it is on the move. The intelligence is not just an algorithm driven based on multiple sensor inputs alone, but here the intelligence need to be highly situational aware and by keeping the current vehicle dynamics. This needs lot situational and scenario based complex computation and communication with multiple Electronic Control Unit (ECU) within the vehicle.

Featured Article

PUF: A Crucial Technology for AI and IoT

One of the key challenges for AIoT is the protection of AI assets. AI functions often need to detect, evaluate and respond in real time. As a result, a critical security concern is the fact that internal databases and interfaces for AI are not suitable for encryption because such an operation would demand too much time and resources.