No Arabic abstract
In this paper, we are interested in building a domain knowledge based deep learning framework to solve the chiller plants energy optimization problems. Compared to the hotspot applications of deep learning (e.g. image classification and NLP), it is difficult to collect enormous data for deep network training in real-world physical systems. Most existing methods reduce the complex systems into linear model to facilitate the training on small samples. To tackle the small sample size problem, this paper considers domain knowledge in the structure and loss design of deep network to build a nonlinear model with lower redundancy function space. Specifically, the energy consumption estimation of most chillers can be physically viewed as an input-output monotonic problem. Thus, we can design a Neural Network with monotonic constraints to mimic the physical behavior of the system. We verify the proposed method in a cooling system of a data center, experimental results show the superiority of our framework in energy optimization compared to the existing ones.
Realization of deep learning with coherent optical field has attracted remarkably attentions presently, which benefits on the fact that optical matrix manipulation can be executed at speed of light with inherent parallel computation as well as low latency. Photonic neural network has a significant potential for prediction-oriented tasks. Yet, real-value Backpropagation behaves somewhat intractably for coherent photonic intelligent training. We develop a compatible learning protocol in complex space, of which nonlinear activation could be selected efficiently depending on the unveiled compatible condition. Compatibility indicates that matrix representation in complex space covers its real counterpart, which could enable a single channel mingled training in real and complex space as a unified model. The phase logical XOR gate with Mach-Zehnder interferometers and diffractive neural network with optical modulation mechanism, implementing intelligent weight learned from compatible learning, are presented to prove the availability. Compatible learning opens an envisaged window for deep photonic neural network.
Neural networks with at least two hidden layers are called deep networks. Recent developments in AI and computer programming in general has led to development of tools such as Tensorflow, Keras, NumPy etc. making it easier to model and draw conclusions from data. In this work we re-approach non-linear regression with deep learning enabled by Keras and Tensorflow. In particular, we use deep learning to parametrize a non-linear multivariate relationship between inputs and outputs of an industrial sensor with an intent to optimize the sensor performance based on selected key metrics.
Owing to the complicated characteristics of 5G communication system, designing RF components through mathematical modeling becomes a challenging obstacle. Moreover, such mathematical models need numerous manual adjustments for various specification requirements. In this paper, we present a learning-based framework to model and compensate Power Amplifiers (PAs) in 5G communication. In the proposed framework, Deep Neural Networks (DNNs) are used to learn the characteristics of the PAs, while, correspondent Digital Pre-Distortions (DPDs) are also learned to compensate for the nonlinear and memory effects of PAs. On top of the framework, we further propose two frequency domain losses to guide the learning process to better optimize the target, compared to naive time domain Mean Square Error (MSE). The proposed framework serves as a drop-in replacement for the conventional approach. The proposed approach achieves an average of 56.7% reduction of nonlinear and memory effects, which converts to an average of 16.3% improvement over a carefully-designed mathematical model, and even reaches 34% enhancement in severe distortion scenarios.
In this paper, we study the multiple-input and multiple-output (MIMO) wireless power transfer (WPT) system so as to enhance the output DC power of the rectennas. To that end, we revisit the rectenna nonlinearity considering multiple receive antennas. Two combining schemes for multiple rectennas at the receiver, DC and RF combinings, are modeled and analyzed. For DC combining, we optimize the transmit beamforming, adaptive to the channel state information (CSI), so as to maximize the total output DC power. For RF combining, we compute a closed-form solution of the optimal transmit and receive beamforming. In addition, we propose a practical RF combining circuit using RF phase shifter and RF power combiner and also optimize the analog receive beamforming adaptive to CSI. We also analytically derive the scaling laws of the output DC power as a function of the number of transmit and receive antennas. Those scaling laws confirm the benefits of using multiple antennas at the transmitter or receiver. They also highlight that RF combining significantly outperforms DC combining since it leverages the rectenna nonlinearity more efficiently. Two types of performance evaluations, based on the nonlinear rectenna model and based on realistic and accurate rectenna circuit simulations, are provided. The evaluations demonstrate that the output DC power can be linearly increased by using multiple rectennas at the receiver and that the relative gain of RF combining versus DC combining in terms of the output DC power level is very significant, of the order of 240% in a one-transmit antenna ten-receive antenna setup.
A key component of deep learning (DL) for natural language processing (NLP) is word embeddings. Word embeddings that effectively capture the meaning and context of the word that they represent can significantly improve the performance of downstream DL models for various NLP tasks. Many existing word embeddings techniques capture the context of words based on word co-occurrence in documents and text; however, they often cannot capture broader domain-specific relationships between concepts that may be crucial for the NLP task at hand. In this paper, we propose a method to integrate external knowledge from medical terminology ontologies into the context captured by word embeddings. Specifically, we use a medical knowledge graph, such as the unified medical language system (UMLS), to find connections between clinical terms in cancer pathology reports. This approach aims to minimize the distance between connected clinical concepts. We evaluate the proposed approach using a Multitask Convolutional Neural Network (MT-CNN) to extract six cancer characteristics -- site, subsite, laterality, behavior, histology, and grade -- from a dataset of ~900K cancer pathology reports. The results show that the MT-CNN model which uses our domain informed embeddings outperforms the same MT-CNN using standard word2vec embeddings across all tasks, with an improvement in the overall micro- and macro-F1 scores by 4.97%and 22.5%, respectively.