Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

Deep learning

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.

/pdf/mastering-the-game-of-go-with-deep-neural-networks-and-tree-3viuxo6uxm.pdf

Mastering the game of Go with deep neural networks and tree search

TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. Tensor-Flow uses dataflow graphs to represent computation, shared state, and the operations that mutate that state. It maps the nodes of a dataflow graph across many machines in a cluster, and within a machine across multiple computational devices, including multicore CPUs, general-purpose GPUs, and custom-designed ASICs known as Tensor Processing Units (TPUs). This architecture gives flexibility to the application developer: whereas in previous "parameter server" designs the management of shared state is built into the system, TensorFlow enables developers to experiment with novel optimizations and training algorithms. TensorFlow supports a variety of applications, with a focus on training and inference on deep neural networks. Several Google services use TensorFlow in production, we have released it as an open-source project, and it has become widely used for machine learning research. In this paper, we describe the TensorFlow dataflow model and demonstrate the compelling performance that TensorFlow achieves for several real-world applications.

/pdf/tensorflow-a-system-for-large-scale-machine-learning-10wgdjhl6k.pdf

TensorFlow: a system for large-scale machine learning

A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks. An even more ambitious goal is to build models that never stop adapting, and that become increasingly more efficient through time by suitably transferring the accrued knowledge. Beyond the study of the actual learning algorithm and model architecture, there are several hurdles towards our quest to build such models, such as the choice of learning protocol, metric of success and data needed to validate research hypotheses. In this work, we introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks, sorted chronologically and extracted from papers sampled uniformly from computer vision proceedings spanning the last three decades. The resulting stream reflects what the research community thought was meaningful at any point in time, and it serves as an ideal test bed to assess how well models can adapt to new tasks, and do so better and more efficiently as time goes by. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. The diversity is also reflected in the wide range of dataset sizes, spanning over four orders of magnitude. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks, yet with a low entry barrier as it is limited to a single modality and well understood supervised learning problems. Moreover, we provide a reference implementation including strong baselines and an evaluation protocol to compare methods in terms of their trade-off between accuracy and compute.

NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

This research examined the relation between dispositional optimism and judgments of future life events and whether this relation is moderated by affective states. In this study the moderating role of experimentally induced affective states, using film clips (N = 259), was investigated. After filling in the questionnaire for dispositional optimism, the participants were randomly assigned in the experimental conditions in order to induce positive versus negative affective states. Finally, the participants filled in the affective states and judgments of future life events scales. The results indicated that the participants with a higher level of optimism had the tendency to judge positive events as more likely and negative events as less likely to happen in the future. We found evidence for affective states as moderators; the association between dispositional optimism and judgments of future positive events depended on experimentally induced affective states. Specifically, in positive affective state condition, the association between dispositional optimism and judgments of future positive events was weaker than in both negative affective state and control conditions. The implications of these findings for understanding the role of optimism and affective states, in determining the judgments about the likelihood of future events are discussed.

Dispositional Optimism and Judgments of Future Life Events: Affective States as Moderators

Until recent years, industrial control systems relied on wires to transfer the process values and control signals through an industrial plant. The use of wireless is limited to monitoring non-critical process values and using it for process control was uncommon for several reasons: complexity of usage, reliability, power consumption and a general doubt on its advantages. Wireless technology has made great progress in terms of usage, low-power capabilities and availability. Furthermore, the microcontrollers which implement the wireless stacks and the core of any wireless network have seen lots of improvements mainly regarding performance and power usage. This paper presents the possible solution to replace standard wire-based control systems with using a low-power ARM Cortex microcontroller and a low-power IEEE 802.15.4 transceiver bundle acting as a wireless node which can do both control calculations and data acquisition used in a traditional control system.

The implementation of an ARM-based low-power wireless process control system

In the past few years, the general interest in connected home, smart devices and appliances has risen significantly. New concepts like the Internet of Things have inspired new applications and research areas for sensors and gathering data from them. One important application that makes use of these new technologies is monitoring indoor air quality, which according to Directive 2010/31/EU of the European Parliament and of the Council, can “reduce mortality, morbidity, and health care costs”. In this context, this paper proposes a solution for wireless monitoring of indoor air quality parameters including temperature, humidity, CO2 and TVOC levels using a low-power ARM Cortex-M microcontroller, an IEEE 802.15.4 sub-GHz transceiver and temperature, humidity and gas sensors and observing the changes in overall power consumption by implementing an adaptive transmit power technique.

Using Adaptive Transmit Power in Wireless Indoor Air Quality Monitoring

The paper presents a Rapid Control Prototyping (RCP) toolbox for Matlab/Simulink, which can be used to generate real-time C code for the Renesas M32C87 microcontroller. The toolbox, Target for Renesas M32C87, contains Simulink blocks, which implement drivers and algorithms specific for the M32C87 processor, grouped in four libraries: I/O drivers, Digital Motor Control (DMC), Controller Area Network (CAN) and Serial Communication Interface (SCI). Control algorithms, for the M32C87 microcontroller can be developed using blocks from the Target for Renesas M32C87 toolbox and predefined blocks from Simulink or user defined blocks. After the validation of the model the cod generation process can be invoked. At the end of the code generation process the High-performance Embedded Workshop (HEW) Integrated Development Environment (IDE) is automatically started, a new HEW project is created, the generated code-source files are added to the project, the project is compiled and the binary file is downloaded to the target processor. The execution of the code can be monitored in real-time using the implemented CAN drivers.

Andrei Rusu

Papers

NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

Dispositional Optimism and Judgments of Future Life Events: Affective States as Moderators

The implementation of an ARM-based low-power wireless process control system

Using Adaptive Transmit Power in Wireless Indoor Air Quality Monitoring

Rapid Control Prototyping toolbox for Renesas M32C87 microcontroller