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

Cette etude cible l’approfondissement des decouvertes pour le role que la personnalite joue sur le comportement de recherche d’emploi. Elle teste l’effet indirect de l’ouverture a l’experience sur l’intensite de la recherche d’un job et l’effort, par la mediation de l’auto efficacite dans la recherche d’un job. Cent trois personnes sans emploi ont fourni les donnees pour cette analyse transversale. Les resultats n’appuient les relations de mediation partielle, mais, contrairement aux hypotheses, elles ont releve des mediations completes. Les resultats montrent que l’ouverture a l’experience joue un role important dans le processus de recherche d’un job, surtout par assurer l’adaptabilite necessaire a l’irregulier et constamment changeable environnement de la recherche d’embauche. En plus, l’auto efficacite dans la recherche d’un job peut aider a la comprehension du processus motivationnel implique dans le lien entre l’ouverture a l’experience et le comportement de recherche d’emploi.

Openness to experience and job search behavior: a study on the mediating effect of job search selfefficacy

One of the most influential constructs in recent social psychology is regulatory focus. However, the Romanian literature on this subject is sparse. After back-translating the Regulatory Focus Questionnaire (RFQ), we explored its factor structure and construct validity in two different studies. In Study 1, 401 students completed the RFQ and the BIS/BAS scales. After excluding one item due to its small loadings on both factors, the exploratory factor analysis and also the confirmatory factor analysis showed that a two-factor structure had the best fit. Results also showed that promotion focus and prevention focus were associated with BAS and BIS in the expected direction. In Study 2, using 198 students, besides the Romanian form of the RFQ we also used the two scales from IPIP 50 for extraversion and emotional stability, and PANAS. We replicated through confirmatory factor analysis the two-factor solution and also found that the instrument has acceptable temporal stability. We also discovered that the relationships between the promotion and the prevention scales with all the other four variables were as reported in other previous studies. The Regulatory Focus Questionnaire – Romanian form holds adequate psychometric properties and certainly can be used in future research, especially on student samples.

Measuring chronic regulatory focus in Romania: adaptation of the Regulatory Focus Questionnaire

We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several com-mon adversarial attacks on CIFAR- 10 classiﬁers for perturbations up to (cid:15) = 8 / 255 in L ∞ norm and (cid:15) = 0 . 5 in L 2 norm. Implicit neural representations are used to approximately encode pixel colour intensities in 2 D images such that classiﬁers trained on transformed data appear to have robustness to small perturbations without adversarial training or large drops in performance. The seed of the random number generator used to initialise and train the implicit neural representation turns out to be necessary information for stronger generic attacks, suggesting its role as a private key . We devise a Parametric Bypass Approximation (PBA) attack strategy for key-based defences, which successfully invalidates an existing method in this category. Interestingly, our LINAC defence also hinders some transfer and adaptive attacks, including our novel PBA strategy. Our results emphasise the importance of a broad range of customised attacks despite apparent robustness according to standard evaluations.

Hindering Adversarial Attacks with Implicit Neural Representations

Evaluative conditioning procedures change people’s evaluations of stimuli that are paired with pleasant or unpleasant items. To test whether influence awareness allows people to resist such persuas...

Beyond contingency awareness: the role of influence awareness in resisting conditioned attitudes

Previous research has mostly focused on the link between the linguistic and behavioral footprints found on social media on the one hand and personality on the other. Despite the high amount of image-based contents posted and shared online and the valuable implicit information they might conceal about users' preferences and tendencies, the study of visual traces is in its infancy. The goal of the current paper is to test whether the color characteristics of the Facebook profile picture could mirror the level of neuroticism on a sample of 508 Romanian users. For this purpose, we assessed the classification performance of four machine learning algorithms having as input three sets of visual features: (1) the colorfulness, which indicates how colorful is an image; (2) the proportion of cold colors, along with the mean and standard deviation for saturation and value; (3) the emotional load, defined as pleasure, arousal, and dominance. None of the models showed good accuracy. However, this paper contributes to the literature by being part of a line of research that requires development not only in Romania but also worldwide.

Andrei Rusu

Papers

Openness to experience and job search behavior: a study on the mediating effect of job search selfefficacy

Measuring chronic regulatory focus in Romania: adaptation of the Regulatory Focus Questionnaire

Hindering Adversarial Attacks with Implicit Neural Representations

Beyond contingency awareness: the role of influence awareness in resisting conditioned attitudes

Detecting Individuals High in Neuroticism based on the Color Features of the Facebook Profile Picture