Change Location × San Francisco

    Recent Locations

      [3 Day Training Course] Machine Learning: San Francisco in San Francisco

      • [3 Day Training Course] Machine Learning: San Francisco Photo #1
      1 of 1
      December 7, 2018

      Friday   9:00 AM

      • No Performers Listed
      [3 Day Training Course] Machine Learning: San Francisco

      Why this training? In this three-day course you will be given clear explanations of machine learning theory, practical scenarios of machine learning algorithms, linear and non-linear regression, overfitting, regularization, loss functions, neural networks, introduction to the backpropagation algorithm and best practices in using different neural networks architectures. The participants will gain experience in machine learning techniques, neural network configuration and model optimization in R and Python. This course is based on hands-on exercises and gives developers an extended overview of various tools, services and frameworks which become essential in machine learning. Who should attend? The Machine Learning training was developed for junior data scientists seeking a better understanding and knowledge of: Basic principles of machine learning How to use and manage tools and frameworks for machine learning Algorithms for building and learning neural networks Course objectives Provide the information and, through labs, the experience necessary for the students to: Gain a basic understanding of machine learning concepts Use main troubleshooting techniques of machine learning Build neural networks with TensorFlow Program Day 1  Introduction Agenda for the training. General introduction for artificial intelligence. What are the advantages and disadvantages of machine learning? Machine learning overview Introduction to the core idea of teaching a computer to learn using data, machine learning tasks and applications. Linear and nonlinear regressions Prediction of a real-valued output based on an input values. Methods for classifying data into discrete outcomes . The danger of overfitting regression models. Regularization Use of regularization in classification. Early stopping as regularization in time. Regularizers for sparsity. Regularizers for multitask learning. Support vector machines Building a model of SVM training algorithm. Linear SVM. Nonlinear classification. Large Margin Classification. Day 2 Neural networks Components of an artificial neural network. Connections and weights. Propagation function. Choosing a cost function. Learning paradigms. Types of neural networks. Activation functions Identity function, unit step (binary step) function, sigmoid function, hyperbolic function, inverse trigonometric function, softmax function, rectified linear unit (ReLU), exponential linear unit (ELU), maxout. Learning of Neural Networks Training, test, and validation sets. Selection of a validation dataset: holdout method and cross-validation. Instance space decomposition. Supervised Learning Labeled training data. Determination of the type of training examples. Gathering a training set. Determination of the input feature representation of the learned function. Running the learning algorithm on the gathered training set. Evaluation of the accuracy of the learned function. Unsupervised Learning Approaches to unsupervised learning. Clustering, anomaly detection, Autoencoders, Generative Adversarial Networks, self-organizing map. Reinforcement Learning Markov decision process. Algorithms for control learning. Criterion of optimality. Brute force approach. Value function approaches. Monte Carlo methods. Temporal difference methods. End-to-end (Deep) reinforcement learning. Day 3 Large Scale Machine Learning Dimensionality Reduction. Stochastic Gradient Descent. Mini-Batch Gradient Descent. Stochastic Gradient Descent Convergence. Convolutional neural networks Machines vision. Convolutional layers, pooling layers, fully connected layers and normalization layers. Number of filters. Filter shape. Hierarchical coordinate frames. Image recognition. Video analysis. Natural language processing. Prerequisites Altoros recommends that all students have: Programming: Basic R and Python programming skills, with the capability to work effectively with data structures Experience with the RStudio and the Jupyter Notebook applications Basic experience with git A basic understanding matrix vector operations and notation A basic knowledge of Statistics Basic command line operations A workstation with the following capabilities: A web browser (Chrome/Firefox) Internet connection A firewall allowing outgoing connections on TCP ports 80 and 443 The following developer utilities should be installed: Anaconda RStudio Jupyter Notebook Payment info: If you would like to get an invoice for your company to pay for this training, please email to and provide us with the following info: Name of your Company/Division which you would like to be invoiced; Name of the person the invoice should be addressed to; Mailing address; Purchase order # to put on the invoice (if required by your company). The tickets are limited, so hurry up to reserve your spot NOW! ! Please note our classes are contingent upon having 7 attendees. If we don't have enough tickets sold, we will cancel the training and refund your money one week prior to the training.Thanks for the understanding.

      Categories: Science

      Event details may change at any time, always check with the event organizer when planning to attend this event or purchase tickets.