Deep Learning Essentials

Description

Deep Learning Modul - University of Oldenburg
Mark Otten
Mind Map by Mark Otten, updated more than 1 year ago
Mark Otten
Created by Mark Otten over 6 years ago
30
0

Resource summary

Deep Learning Essentials
  1. 7 - Convolutional Networks
    1. Handling
      1. Layer
        1. Activation
          1. Padding
            1. k = (d-m+2p)/s+1

              Annotations:

              • Wird noch korrigiert. Falsche Formel
            2. Stride
              1. Employes a vertical and horizonal axis
                1. The number of steps a kernel is moved over the input activation matrix is called stride s.
              2. Pooling
                1. reduce the dimensionlity
                2. Convolution
                  1. AlexNET - 2012
                  2. 6 - Model Assessment
                    1. 5 - Model Training
                      1. 4 - Weight Adaptation
                        1. 3 - Multilayer Perceptron
                          1. 2 - Linear Models
                            1. Supervised Learning
                              1. Learning with labels
                                1. each pattern x has a label information y
                                  1. pair (x_i, y_i)
                                    1. training set
                                      1. ground truth
                                      2. pair (x'_i, y'_i)
                                        1. predict set
                                        2. If the label is discrete, e.g., {0, 1} or {muffin, chihuahua}, the learning problem is called classification
                                          1. classificatoin
                                          2. if hoices is explored ol detection. continuous First, (y ∈ R) it is called regression.
                                            1. regression
                                        3. Linear Regression
                                          1. found in natural and technical processes
                                            1. The basic linear model (1)
                                              1. x € IR
                                                1. weight factor
                                                  1. w € IR called slope
                                                  2. parameter
                                                    1. b € IR called inter
                                                    2. linear relationship
                                                    3. Least Squares
                                                      1. With First, the least squares formulation, the coefficients can be derived. (2)
                                                        1. means squared error (MSE)
                                                        2. Linear Regression Coefficients
                                                          1. Weight and intercept can be mathematically derived as (3)
                                                            1. x Strich mens x_1 ... x_n and the same for the label y Strich
                                                          2. Example Fit, Illustration of linear model that is fiied to the patterns minimizing the MSE
                                                          3. Nearest Neighbors
                                                            1. K-nearest neighbors (kNN) searches for labels based on nieghborhoods in data space.
                                                          4. 1 - Introduction
                                                            1. A.I.
                                                              1. Intelligence is
                                                                1. learn from observations
                                                                  1. others experiences
                                                                    1. own experiences
                                                                  2. related to
                                                                    1. Data Science
                                                                      1. Big Data
                                                                    2. Technologies
                                                                      1. deep learning
                                                                        1. TFlearn
                                                                          1. Keras
                                                                            1. Tensorflow
                                                                            2. mashine learning
                                                                              1. scikit-learn
                                                                              2. share on github
                                                                                1. devlopment of scripts
                                                                                  1. Jupyter
                                                                                  2. Research
                                                                                    1. archivx
                                                                                    2. Powerfull Hardware
                                                                                      1. AWS
                                                                                        1. NVIDIA GRPUs
                                                                                    3. 8 - Neuroevolution
                                                                                      1. Genetic Alogrithm
                                                                                        1. mimicking biological evolution
                                                                                          1. Crossover
                                                                                            1. Mutation
                                                                                              1. Selection
                                                                                              2. Optimization
                                                                                                1. examples
                                                                                              3. 9 - Auto-encoder
                                                                                                1. 10 - Generative Adversarial Networks
                                                                                                  Show full summary Hide full summary

                                                                                                  Similar

                                                                                                  Tiefergreifendes Lernen - Wie umsetzen?
                                                                                                  Laura Overhoff
                                                                                                  U9 Corporate Identity
                                                                                                  Lena A.
                                                                                                  POLKO
                                                                                                  Sabine B.
                                                                                                  Inteligencia artificial
                                                                                                  Natalia Rueda
                                                                                                  Genetic Algorithm Essentials
                                                                                                  Mark Otten
                                                                                                  A.I - Artificial Intelligence
                                                                                                  Yanik Emmenegger
                                                                                                  wichtige großen BLA
                                                                                                  gary timeless
                                                                                                  Artificial Intelligence - English
                                                                                                  Yanik Emmenegger
                                                                                                  Schulregeln
                                                                                                  Silke Fuchs
                                                                                                  erste Woche
                                                                                                  gary timeless
                                                                                                  Mindmap WiFree-Game
                                                                                                  Oliver Lutz