Sirine Amraneunderstanding layers in dl : input, hidden, and output layersa neural network is structured in successive layers that process data hierarchically. each layer consists of neurons that perform…Feb 2Feb 2
Sirine Amraneloss functions in ml and dl, part 1 : huber loss, quantile loss, tweedie loss, log-cosh lossin regression models, the choice of the loss function directly influences the stability and accuracy of predictions. a poor selection can…Feb 111Feb 111
Sirine Amraneactivation functions, part 3 : linear and softplus for regression output layer in dlin deep learning, choosing the right activation function for regression is essential. the linear activation is the standard choice as itFeb 10Feb 10
Sirine AmraneIntroduction to Recurrent Neural Networks: Classic RNN, LSTM, and GRUIn the world of deep learning, sequences are everywhere. To understand these sequences and leverage them, we need models capable of…Jan 23Jan 23
Sirine AmraneHow do you beat overfitting in Deep Learning ? Part 1 : DropoutUnderstanding Dropout for a better generalizationJan 21Jan 21
Sirine AmraneTransformers in Machine Learning: introduction (1/5)Since their introduction, transformers have revolutionized the field of artificial intelligence, especially in natural language processing…Jan 20Jan 20
Sirine AmraneTransformers : optimizing efficiency and precision with hybrid models, introduction (1/2)What is a hybrid model ?Jan 21Jan 21
Sirine Amraneoptimization algorithms in ml : gradient descent — and dl : stochastic gradient descent, adamoptimization algorithms are at the heart of deep learning. they allow us to adjust a model’s parameters to achieve the best possible…Feb 3Feb 3
