scholarly journals The Foundations of Deep Learning with a Path Towards General Intelligence

2018 ◽  
pp. 162-173 ◽  
Author(s):  
Eray Özkural
Keyword(s):  
Deep Learning ◽  
General Intelligence

scholarly journals The unreasonable effectiveness of deep learning in artificial intelligence

2020 ◽  
Vol 117 (48) ◽  
pp. 30033-30038 ◽  
Author(s):  
Terrence J. Sejnowski
Keyword(s):  
Deep Learning ◽  
Optimization Theory ◽  
Brain Regions ◽  
Network Architectures ◽  
General Intelligence ◽  
Sample Complexity ◽  
Learning Networks ◽  
Digital Devices ◽  
Unreasonable Effectiveness ◽  
Real World Problems

Deep learning networks have been trained to recognize speech, caption photographs, and translate text between languages at high levels of performance. Although applications of deep learning networks to real-world problems have become ubiquitous, our understanding of why they are so effective is lacking. These empirical results should not be possible according to sample complexity in statistics and nonconvex optimization theory. However, paradoxes in the training and effectiveness of deep learning networks are being investigated and insights are being found in the geometry of high-dimensional spaces. A mathematical theory of deep learning would illuminate how they function, allow us to assess the strengths and weaknesses of different network architectures, and lead to major improvements. Deep learning has provided natural ways for humans to communicate with digital devices and is foundational for building artificial general intelligence. Deep learning was inspired by the architecture of the cerebral cortex and insights into autonomy and general intelligence may be found in other brain regions that are essential for planning and survival, but major breakthroughs will be needed to achieve these goals.

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

The Effect of Retest Practice on the Speed-Ability Relationship

2004 ◽  
Vol 9 (1) ◽  
pp. 24-31 ◽  
Author(s):  
Sybille Rockstroh ◽  
Karl Schweizer
Keyword(s):  
Reaction Time ◽  
Skill Acquisition ◽  
Reaction Times ◽  
Cognitive Tasks ◽  
General Intelligence ◽  
Attention Switching ◽  
Letter Comparison ◽  
Sternberg Paradigm ◽  
The Relationship ◽  
Elementary Cognitive Tasks

Effects of four retest-practice sessions separated by 2 h intervals on the relationship between general intelligence and four reaction time tasks (two memory tests: Sternberg's memory scanning, Posner's letter comparison; and two attention tests: continuous attention, attention switching) were examined in a sample of 83 male participants. Reaction times on all tasks were shortened significantly. The effects were most pronounced with respect to the Posner paradigm and smallest with respect to the Sternberg paradigm. The relationship to general intelligence changed after practice for two reaction time tasks. It increased to significance for continuous attention and decreased for the Posner paradigm. These results indicate that the relationship between psychometric intelligence and elementary cognitive tasks depends on the ability of skill acquisition. In the search for the cognitive roots of intelligence the concept of learning seems to be of importance.

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document