This paper reports on field-effect-transistor-based terahertz detectors for the operation at discrete frequencies spanning from 0.2 to 4.3 THz. They are implemented using a 150-nm CMOS process technology, employ self-mixing in the n-channels of the transistors and operate well above the transistors' cutoff frequency. The theoretical description of device operation by Dyakonov and Shur is extended in order to describe the device impedance, responsivity, and noise-equivalent power for a novel detection concept, which couples the signal to the drain. This approach enables quasi-static (QS) detection and calibration of the detectors. The different transport regimes (i.e., QS, distributed resistive, and plasmonic mixing) and their transitions are theoretically discussed and experimentally accessed. Responsivity values of 350 V/W at 595 GHz, 30 V/W at 2.9 THz, and 5 V/W at 4.1 THz are reported. At 0.595 THz, we determine the optical noise equivalent power (NEP) to be 42 pW/√Hz ; at 2.9 THz, the value is 487 pW/√Hz. All values are reported for optimum gate bias with respect to NEP at 295 K. For 0.595 THz, theory predicts a NEP value at threshold as low as 2 pW/√Hz for ideal coupling of the radiation.
Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is investigated. The core challenge is framed as protecting previously acquired representations from being catastrophically forgotten. However, comparison of individual methods is nevertheless performed in isolation from the real world by monitoring accumulated benchmark test set performance. The closed world assumption remains predominant, i.e. models are evaluated on data that is guaranteed to originate from the same distribution as used for training. This poses a massive challenge as neural networks are well known to provide overconfident false predictions on unknown and corrupted instances. In this work we critically survey the literature and argue that notable lessons from open set recognition, identifying unknown examples outside of the observed set, and the adjacent field of active learning, querying data to maximize the expected performance gain, are frequently overlooked in the deep learning era. Hence, we propose a consolidated view to bridge continual learning, active learning and open set recognition in deep neural networks. Finally, the established synergies are supported empirically, showing joint improvement in alleviating catastrophic forgetting, querying data, selecting task orders, while exhibiting robust open world application.
Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surface markings as well as the possibility for different types of defects to overlap, make it a challenging real-world task. In this work we introduce the novel COncrete DEfect BRidge IMage dataset (CODEBRIM) for multi-target classification of five commonly appearing concrete defects. We investigate and compare two reinforcement learning based meta-learning approaches, MetaQNN and efficient neural architecture search, to find suitable convolutional neural network architectures for this challenging multi-class multi-target task. We show that learned architectures have fewer overall parameters in addition to yielding better multi-target accuracy in comparison to popular neural architectures from the literature evaluated in the context of our application.
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
9 January 2014 in Journal of Infrared, Millimeter, and Terahertz Waves