Rule-based machine learningRule-based machine learning (RBML) is a term in computer science intended to encompass any machine learning method that identifies, learns, or evolves 'rules' to store, manipulate or apply. The defining characteristic of a rule-based machine learner is the identification and utilization of a set of relational rules that collectively represent the knowledge captured by the system. This is in contrast to other machine learners that commonly identify a singular model that can be universally applied to any instance in order to make a prediction.
Labeled dataLabeled data is a group of samples that have been tagged with one or more labels. Labeling typically takes a set of unlabeled data and augments each piece of it with informative tags. For example, a data label might indicate whether a photo contains a horse or a cow, which words were uttered in an audio recording, what type of action is being performed in a video, what the topic of a news article is, what the overall sentiment of a tweet is, or whether a dot in an X-ray is a tumor.
Random fieldIn physics and mathematics, a random field is a random function over an arbitrary domain (usually a multi-dimensional space such as ). That is, it is a function that takes on a random value at each point (or some other domain). It is also sometimes thought of as a synonym for a stochastic process with some restriction on its index set. That is, by modern definitions, a random field is a generalization of a stochastic process where the underlying parameter need no longer be real or integer valued "time" but can instead take values that are multidimensional vectors or points on some manifold.
Recherche automatique d'architecture neuronaleLa recherche automatique d'architecture neuronale (Neural Architecture Search, NAS) est un ensemble de techniques visant à découvrir automatiquement de nouveaux modèles de réseaux de neurones artificiels. Les principales méthodes employées dans la littérature sont basées soit sur de l'apprentissage par renforcement, sur de la descente de gradient ou bien sur des algorithmes génétiques. Plusieurs méthodes NAS parviennent à obtenir des architectures qui atteignent ou surpassent les performances des modèles créés à la main.
Batch normalizationBatch normalization (also known as batch norm) is a method used to make training of artificial neural networks faster and more stable through normalization of the layers' inputs by re-centering and re-scaling. It was proposed by Sergey Ioffe and Christian Szegedy in 2015. While the effect of batch normalization is evident, the reasons behind its effectiveness remain under discussion. It was believed that it can mitigate the problem of internal covariate shift, where parameter initialization and changes in the distribution of the inputs of each layer affect the learning rate of the network.
Auto-encodeur variationnelEn apprentissage automatique, un auto-encodeur variationnel (ou VAE de l'anglais variational auto encoder), est une architecture de réseau de neurones artificiels introduite en 2013 par D. Kingma et M. Welling, appartenant aux familles des modèles graphiques probabilistes et des méthodes bayésiennes variationnelles. Les VAE sont souvent rapprochés des autoencodeurs en raison de leur architectures similaires. Leur utilisation et leur formulation mathématiques sont cependant différentes.
Neural tangent kernelIn the study of artificial neural networks (ANNs), the neural tangent kernel (NTK) is a kernel that describes the evolution of deep artificial neural networks during their training by gradient descent. It allows ANNs to be studied using theoretical tools from kernel methods. In general, a kernel is a positive-semidefinite symmetric function of two inputs which represents some notion of similarity between the two inputs. The NTK is a specific kernel derived from a given neural network; in general, when the neural network parameters change during training, the NTK evolves as well.
Seq2seqSeq2seq is a family of machine learning approaches used for natural language processing. Applications include language translation, , conversational models, and text summarization. The algorithm was developed by Google for use in machine translation. Similar earlier work includes Tomáš Mikolov's 2012 PhD thesis. In 2019, Facebook announced its use in symbolic integration and resolution of differential equations. The company claimed that it could solve complex equations more rapidly and with greater accuracy than commercial solutions such as Mathematica, MATLAB and Maple.
Surrogate modelA surrogate model is an engineering method used when an outcome of interest cannot be easily measured or computed, so an approximate mathematical model of the outcome is used instead. Most engineering design problems require experiments and/or simulations to evaluate design objective and constraint functions as a function of design variables. For example, in order to find the optimal airfoil shape for an aircraft wing, an engineer simulates the airflow around the wing for different shape variables (length, curvature, material, .
Graph neural networkA graph neural network (GNN) is a class of artificial neural networks for processing data that can be represented as graphs. In the more general subject of "geometric deep learning", certain existing neural network architectures can be interpreted as GNNs operating on suitably defined graphs. Convolutional neural networks, in the context of computer vision, can be seen as a GNN applied to graphs structured as grids of pixels. Transformers, in the context of natural language processing, can be seen as GNNs applied to complete graphs whose nodes are words in a sentence.
