{"id":141,"date":"2021-05-23T15:51:17","date_gmt":"2021-05-23T15:51:17","guid":{"rendered":"http:\/\/ai.navagne.com\/?page_id=141"},"modified":"2021-05-25T19:20:20","modified_gmt":"2021-05-25T17:20:20","slug":"ai-deep-learning","status":"publish","type":"page","link":"http:\/\/ai.navagne.com\/index.php\/ai-deep-learning\/","title":{"rendered":"AI & Deep learning"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t

AI & Deep Learning - General Concepts<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t

Architecture<\/b> : the organization of the model. It range from very simple structures like standard decision trees<\/em>, Support Vector Machine<\/em> (SVM) and\u00a0 neural network to highly complex ones involving among others GRU<\/em>, LSTM<\/em> and CNN<\/em> networks, GAN<\/em> structures ,\u2026<\/p>

Artificial Intelligence <\/b>(AI<\/strong>) : refers to the ability of a computer or a machine to mimic or even over-perform human intelligence in complex cognitive functions and tasks<\/p>

Backpropagation<\/b> : algorithm widely used with neural networks for training\u00a0 feedforward models<\/p>

Classification<\/b> : technique for identifying to which of a set of possible categories an observation belongs<\/p>

Deep learning <\/b>(DL<\/strong>) : subset of the machine learning<\/em> that involves deep or complex techniques, usually neural networks with complex architectures<\/p>

Gradient descent <\/b>: optimization algorithm with iterative function used to find minima of differentiable loss functions<\/em><\/p>

Hyper-parameters<\/b> : technical parameters of an AI model. As various architectures or techniques might be used, the list of hyper-parameters is very broad. They are often opposed to the \u2018parameters\u2019 that are non-AI-model specific<\/p>

Machine learning <\/b>(ML<\/strong>) : is a subset of AI<\/em> that focuses on the ability of machines or computers to learn complex cognitive functions<\/p>

Neural network<\/strong> (NN<\/strong> or ANN<\/strong>) : is an AI set of algorithmic techniques vaguely mimicking the humain brain functioning that\u00a0<\/p>

Overfitting<\/b> : problem encountered in machine learning<\/em> when the model is very efficient with the training set but performs poorly with the test set. \u201cHigh variance\u201d is often used to describe overfitting problem<\/p>

Regression<\/b> : technique for estimating the relationship between a dependent variable \u2018y\u2019 and independent variable(s) Xi<\/p>

Reinforcement learning <\/b>: technique of machine learning<\/em> dedicated to guide an \u2018intelligent agent\u2019 to maximize cumulative rewards for its actions\/decisions. Reinforcement learning is the third main domain of ML together with supervised learning<\/em> and unsupervised learning<\/em><\/p>

Replicability<\/b> : ability to obtain similar results with similar but not identical parameters and similar data<\/p>

Reproducibility<\/b> : ability to obtain exactly the same results when the model is tested by a different person and \/ or on a different computer<\/p>

Supervised learning <\/b>: \u00a0machine learning\u00a0task of learning a function that maps an input to an output based on examples of input-output pairs.\u00a0It infers a function from\u00a0labeled\u00a0training set that is then applied to non-labeled test dataset<\/p>

Underfitting<\/b> : problem encountered in machine learning when the model is not efficient with the training set and does not reach a satisfactory result. This often occurs when the model is not deep or complex enough to apprehend the embedded complexity of the data. \u201cHigh bias\u201d is often used to refer to underfitting problems<\/p>

Unsupervised learning <\/b>: machine learning\u00a0task of learning a function that maps an input to an output based on examples of input-output pairs.\u00a0It infers a function from\u00a0labeled\u00a0training set that is then applied to non-labeled test dataset<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

AI & Deep Learning – General Concepts Architecture : the organization of the model. It range from very simple structures like standard decision trees, Support Vector Machine (SVM) and\u00a0 neural network to highly complex ones involving among others GRU, LSTM and CNN networks, GAN structures ,\u2026 Artificial Intelligence (AI) : refers to the ability of …<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0},"_links":{"self":[{"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/pages\/141"}],"collection":[{"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/comments?post=141"}],"version-history":[{"count":19,"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/pages\/141\/revisions"}],"predecessor-version":[{"id":298,"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/pages\/141\/revisions\/298"}],"wp:attachment":[{"href":"http:\/\/ai.navagne.com\/index.php\/wp-json\/wp\/v2\/media?parent=141"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}