“…The ISSAC meeting is a showcase for original research contributions on all aspects of computer algebra and symbolic mathematical computation, including: Algorithmic aspects: Exact and symbolic linear, polynomial and differential algebra Symbolic-numeric, homotopy, perturbation and series methods Computational algebraic geometry, group theory and number theory, quantifier elimination and logic Computer arithmetic Summation, recurrence equations, integration, solution of ODEs &PDEs Symbolic methods in other areas of pure and applied mathematics Complexity of algebraic algorithms and algebraic complexity Software aspects: Design of symbolic computation packages and systems Language design and type systems for symbolic computation Data representation Considerations for modern hardware Algorithm implementation and performance tuning Mathematical user interfaces Use with systems for, e.g., digital libraries, courseware, simulation and optimization, automated theorem-proving, computer-aided design, and automatic differentiation Application aspects: Applications that stretch the current limits of computer algebra algorithms or systems, use computer algebra in new areas or new ways, or apply it in situations with broad impact The conference presented a range of invited talks, tutorials, poster sessions, software demonstrations, and vendor exhibits, with its center-piece being peer-reviewed contributed research papers…”

“…The ISSAC meeting is a showcase for original research contributions on all aspects of computer algebra and symbolic mathematical computation, including: Algorithmic aspects: •Exact and symbolic linear, polynomial and differential algebra •Symbolic-numeric, homotopy, perturbation and series methods •Computational algebraic geometry, group theory and number theory, quantifier elimination and logic •Computer arithmetic •Summation, recurrence equations, integration, solution of ODEs & PDEs •Symbolic methods in other areas of pure and applied mathematics •Complexity of algebraic algorithms and algebraic complexity Software aspects: •Design of symbolic computation packages and systems •Language design and type systems for symbolic computation •Data representation •Considerations for modern hardware •Algorithm implementation and performance tuning •Mathematical user interfaces •Use with systems for, e.g., digital libraries, course-ware, simulation and optimization, automated theoremproving, computer-aided design, and automatic differentiation Application aspects: •Applications that stretch the current limits of computer algebra algorithms or systems, use computer algebra in new areas or new ways, or apply it in situations with broad impact…”

Tabla de Contenidos: “…-- Advantages over traditional shallow methods -- Impact of deep learning -- The motivation of deep architecture -- The neural viewpoint -- The representation viewpoint -- Distributed feature representation -- Hierarchical feature representation -- Applications -- Lucrative applications -- Success stories -- Deep learning for business -- Future potential and challenges -- Summary -- Chapter 2: Getting Yourself Ready for Deep Learning -- Basics of linear algebra -- Data representation -- Data operations -- Matrix properties -- Deep learning with GPU -- Deep learning hardware guide -- CPU cores -- RAM size -- Hard drive -- Cooling systems -- Deep learning software frameworks -- TensorFlow - a deep learning library -- Caffe -- MXNet -- Torch -- Theano -- Microsoft Cognitive Toolkit -- Keras -- Framework comparison -- Setting up deep learning on AWS -- Setup from scratch -- Setup using Docker -- Summary -- Chapter 3: Getting Started with Neural Networks -- Multilayer perceptrons -- The input layer -- The output layer -- Hidden layers -- Activation functions -- Sigmoid or logistic function -- Tanh or hyperbolic tangent function -- ReLU -- Leaky ReLU and maxout -- Softmax -- Choosing the right activation function -- How a network learns -- Weight initialization -- Forward propagation -- Backpropagation -- Calculating errors -- Backpropagation -- Updating the network -- Automatic differentiation -- Vanishing and exploding gradients -- Optimization algorithms -- Regularization -- Deep learning models -- Convolutional Neural Networks -- Convolution -- Pooling/subsampling -- Fully connected layer -- Overall…”