Neural computing – Data science Schulung

Alle Preise zzgl. MwSt

Kurs Code

Nue_LBG

Dauer

14 hours (üblicherweise 2 Tage inklusive Pausen)

Voraussetzungen

Knowledge/appreciation of machine learning, systems architecutre and programming languages are desirable

Überblick

Diese auf Klassenräumen basierende Schulungssitzung enthält Präsentationen und computergestützte Beispiele sowie Fallstudien, die mit relevanten neuronalen und tiefen Netzwerkbibliotheken durchgeführt werden sollen

Machine Translated

Schulungsübersicht

  1. Overview of neural networks and deep learning
    • The concept of Machine Learning (ML)
    • Why we need neural networks and deep learning?
    • Selecting networks to different problems and data types
    • Learning and validating neural networks
    • Comparing logistic regression to neural network
  2. Neural network
    • Biological inspirations to Neural network
    • Neural Networks– Neuron, Perceptron and MLP(Multilayer Perceptron model)
    • Learning MLP – backpropagation algorithm
    • Activation functions – linear, sigmoid, Tanh, Softmax
    • Loss functions appropriate to forecasting and classification
    • Parameters – learning rate, regularization, momentum
    • Building Neural Networks in Python
    • Evaluating performance of neural networks in Python
  3. Basics of Deep Networks
    • What is deep learning?
    • Architecture of Deep Networks– Parameters, Layers, Activation Functions, Loss functions, Solvers
    • Restricted Boltzman Machines (RBMs)
    • Autoencoders
  4. Deep Networks Architectures
    • Deep Belief Networks(DBN) – architecture, application
    • Autoencoders
    • Restricted Boltzmann Machines
    • Convolutional Neural Network
    • Recursive Neural Network
    • Recurrent Neural Network
  5. Overview of libraries and interfaces available in Python
    • Caffee
    • Theano
    • Tensorflow
    • Keras
    • Mxnet
    • Choosing appropriate library to problem
  6. Building deep networks in Python
    • Choosing appropriate architecture to given problem
    • Hybrid deep networks
    • Learning network – appropriate library, architecture definition
    • Tuning network – initialization, activation functions, loss functions, optimization method
    • Avoiding overfitting – detecting overfitting problems in deep networks, regularization
    • Evaluating deep networks
  7. Case studies in Python
    • Image recognition – CNN
    • Detecting anomalies with Autoencoders
    • Forecasting time series with RNN
    • Dimensionality reduction with Autoencoder
    • Classification with RBM

 

Erfahrungsberichte

★★★★★
★★★★★

Verwandte Kategorien

Kombinierte Kurse

Sonderangebote

Sonderangebote Newsletter

Wir behandeln Ihre Daten vertraulich und werden sie nicht an Dritte weitergeben.
Sie können Ihre Einstellungen jederzeit ändern oder sich ganz abmelden.

EINIGE UNSERER KUNDEN

is growing fast!

We are looking for a good mixture of IT and soft skills in Switzerland!

As a NobleProg Trainer you will be responsible for:

  • delivering training and consultancy Worldwide
  • preparing training materials
  • creating new courses outlines
  • delivering consultancy
  • quality management

At the moment we are focusing on the following areas:

  • Statistic, Forecasting, Big Data Analysis, Data Mining, Evolution Alogrithm, Natural Language Processing, Machine Learning (recommender system, neural networks .etc...)
  • SOA, BPM, BPMN
  • Hibernate/Spring, Scala, Spark, jBPM, Drools
  • R, Python
  • Mobile Development (iOS, Android)
  • LAMP, Drupal, Mediawiki, Symfony, MEAN, jQuery
  • You need to have patience and ability to explain to non-technical people

To apply, please create your trainer-profile by going to the link below:

Apply now!

This site in other countries/regions