We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

http://www.cnbc.pt/jpmatos/29.%20Bradley.pdf?origin=publicationDetail

Measuring emotion: The self-assessment manikin and the semantic differential

Well-being : the foundations of hedonic psychology

Emotion and motivation: measuring affective perception.

This analysis postulates a motivational continuity from reflex reactions to complex, cognitively elaborated emotional expressions. Responses are motivated by either the positive-appetitive or the negative-aversive brain systems. Reflexes evoked during emotional processing are augmented if their affective valence (positive or negative) matches that of the active motivational system and inhibited when a mismatch is present. Research testing this biphasic model is described using the defensive startle probe reflex. It is shown that probe responses are reliably potentiated during perception and imagery of unpleasant events and reduced during pleasant events. The neurobehavioral foundations of this conception are presented, and the implications of probe analysis are elucidated for theories of emotion organization, the assessment of mood, and practical applications in psychopathology and neurological disorder.

A Motivational Analysis of Emotion: Reflex-Cortex Connections

A two-process account of long-term serial position effects

Despite considerable evidence that psychopathic criminals are deviant in their emotional reactions, few studies have examined responses to both pleasurable and aversive stimuli or assessed the role of different facets of psychopathy in affective deviations. This study investigated physiological reactions to emotional sounds in prisoners selected according to scores on the 2 factors of Hare’s Psychopathy Checklist—Revised (PCL–R; R. D. Hare, 1991). Offenders high on the PCL-R emotional–interpersonal factor, regardless of scores on the social deviance factor, showed diminished skin conductance responses to both pleasant and unpleasant sounds, suggesting a deficit in the action mobilization component of emotional response. Offenders who scored high only on the social deviance factor showed a delay in heart rate differentiation between affective and neutral sounds. These findings indicate abnormal reactivity to both positive and negative emotional stimuli in psychopathic individuals, and suggest differing roles for the 2 facets of psychopathy in affective processing deviations. Cleckley (1976) characterized psychopathy as a “mask of sanity” in which overtly normal intelligence and verbal presentation disguise a severe underlying pathology. Cleckley theorized that the disjunction between the psychopath’s surface demeanor and his or her self-defeating actions and disturbed interpersonal relations reflected a fundamental disconnection between cognition and affect. Research to date has provided considerable support for this conceptualization, including findings of reduced electrodermal reactivity to cues signaling noxious stimulation (cf. Arnett, 1997; Hare, 1978; Siddle & Trasler, 1981), reduced electrocortical discrimination between affective and neutral words (e.g., Kiehl, Hare, McDonald, & Brink, 1999; Williamson, Harpur, & Hare, 1991), and diminished potentiation of the defensive startle reflex during exposure to aversive emotional pictures or warning cues (Levenston, Patrick, Bradley, & Lang, 2000; Patrick, 1994; Patrick, Bradley, & Lang, 1993). A limitation of this existing literature is that most published studies have assessed reactivity to unpleasant emotional cues only, typically in the context of conditioning or quasi-conditioning (stressor anticipation) paradigms. Only a few studies have examined responses to appetitive as well as aversive stimuli, and all of these have used visual affective stimuli. The current study extended the existing literature by investigating physiological reactions to both pleasurable and aversive acoustic stimuli in psychopathic individuals.

/pdf/psychopathy-and-physiological-response-to-emotionally-1q6bgd69qc.pdf

Psychopathy and Physiological Response to Emotionally Evocative Sounds.

This chapter reviews research that focuses on the effects of emotionality of single words, and of simple phrases, on event-related brain potentials when these are presented visually in various tasks. In these studies, presentation of emotionally evocative language material has consistently elicited a late (c. 300-600 ms post-onset) positive-going, largely frontal-central shift in the event-related potentials (ERPs), relative to neutral materials. Overall, affectively pleasant and unpleasant words or phrases are quite similar in their neuroelectric profiles and rarely differ substantively. This emotionality effect is enhanced in both amplitude and latency when emotional content is task relevant, but is also reliably observed when the task involves other semantically engaging tasks. On the other hand, it can be attenuated or eliminated when the task does not involve semantic evaluation (e.g., lexical decisions to words or orthographic judgments to the spelling patterns) or when comprehension of phrases requires integration of the connotative meaning of several words (e.g., compare dead puppy and dead tyrant). Taken together, these studies suggest that the emotionality of written language has a rapid and robust impact on ERPs, which can be modulated by specific task demands as well as the linguistic context in which the affective stimulus occurs.

Margaret M. Bradley

Papers

Emotion and motivation: measuring affective perception.

A Motivational Analysis of Emotion: Reflex-Cortex Connections

A two-process account of long-term serial position effects

Psychopathy and Physiological Response to Emotionally Evocative Sounds.

Event-related potential studies of language and emotion: words, phrases, and task effects.