In recent years, Automated Machine Learning (AutoML) has become increasingly important in Computer Science due to the valuable potential it offers. This is testified by the high number of works published in the academic field and the significant efforts made in the industrial sector. However, some problems still need to be resolved. In this paper, we review some Machine Learning (ML) models and methods proposed in the literature to analyze their strengths and weaknesses. Then, we propose their use—alone or in combination with other approaches—to provide possible valid AutoML solutions. We analyze those solutions from a theoretical point of view and evaluate them empirically on three Atari games from the Arcade Learning Environment. Our goal is to identify what, we believe, could be some promising ways to create truly effective AutoML frameworks, therefore able to replace the human expert as much as possible, thereby making easier the process of applying ML approaches to typical problems of specific domains. We hope that the findings of our study will provide useful insights for future research work in AutoML.

Vestibular processing is fundamental to our sense of orientation in space which is a core aspect of the representation of the self. Vestibular information is processed in a large subcortical-cortical neural network. Tasks requiring mental rotations of human bodies in space are known to activate neural regions within this network suggesting that vestibular processing is involved in the control of mental rotation. We studied whether mental rotation is impaired in patients suffering from two different forms of unilateral vestibular disorders (Vestibular Neuritis – VN- and Benign Paroxysmal positional Vertigo – BPPV) with respect to healthy matched controls (C). We used two mental rotation tasks in which participants were required to: i) mentally rotate their own body in space (egocentric rotation) thus using vestibular processing to a large extent and ii) mentally rotate human figures (allocentric rotation) thus using own body representations to a smaller degree. Reaction times and accuracy of responses showed that VN and BPPV patients were impaired in both tasks with respect to C. Significantly, the pattern of results was similar in the three groups suggesting that patients were actually performing the mental rotation without using a different strategy from the control individuals. These results show that dysfunctional vestibular inflow impairs mental rotation of both own body and human figures suggesting that unilateral acute disorders of the peripheral vestibular input massively affect the cerebral processes underlying mental rotations.

Objective: Considering the altered multisensory signal compensation during senescence, the aim of the present study was to evaluate the integration rearrangements in unilateral vestibular hypofunction (UVH) during age-related cognitive decline. Study Design: Cross-sectional study. Setting: Longitudinal cohort study unit and of University tertiary referral center. Patients: Older UVH individuals ≥ 55 years with Mild Cognitive Impairment (MCI) or Alzheimer Disease (AD) and matched UVH control group with age-appropriate cognitive function. Intervention: Vestibulo-ocular reflex, postural sway examination (respectively performed by means of video head impulse test and static posturography), and dizziness-related and quality of life scores were collected in all three groups of UVH patients cognitively evaluated by means of Mini Mental State Examination and Alzheimer's Disease Assessment Scale (ADAS-cog). Main Outcome Measures: Vestibulo-ocular reflex gain, length, surface, and spectral values of body oscillation were measured. Dizziness Handicap Inventory, Activities-specific Balance Confidence scale, and Dynamic Gait Index scores were collected. Results: A significant (p < 0.05) increase in surface and length values during both eyes closed and eyes open conditions was found when comparing scores for AD to both MCI and control group patients, respectively. These patients demonstrated significantly (p < 0.05) lower spectral values of body oscillation on posturography platform in both eyes closed and eyes open condition within the low-frequency interval than MCI and AD patients. Conclusion: This is the first study reporting an association between cognitive decline and posturography parameters with possible preventive clinical implications in evaluating the risk for falls in high-risk patients, such as older adults with common neuro-otological disorders.