Sale!

Deep Learning 1st Edition by Ian Goodfellow, Yoshua Bengio, Aaron Courville ISBN 9780262337373 0262337371

Original price was: $70.00.Current price is: $24.99.

Instant download Deep Learning 0262035618 after payment

SKU: EB_107594 Category:

Deep Learning 1st Edition by Ian Goodfellow, Yoshua Bengio, Aaron Courville – Ebook PDF Instant Download/Delivery: 9780262337373 ,0262337371
Full dowload Deep Learning 1st Edition after payment

Cover image: Deep Learning
Product details:
ISBN 10: 0262337371
ISBN 13: 9780262337373 
Author: Ian Goodfellow, Yoshua Bengio, Aaron Courville

  1. An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives. “Written by three experts in the field, Deep Learning is the only comprehensive book on the subject.” —Elon Musk, cochair of OpenAI; cofounder and CEO of Tesla and SpaceX Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning 1st Edition Table of contents:

    1. Who Should Read This Book?
    2. Historical Trends in Deep Learning
    3. Applied Math and Machine Learning Basics
    4. Linear Algebra
    5. Scalars, Vectors, Matrices and Tensors
    6. Multiplying Matrices and Vectors
    7. Identity and Inverse Matrices
    8. Linear Dependence and Span
    9. Norms
    10. Special Kinds of Matrices and Vectors
    11. Eigendecomposition
    12. Singular Value Decomposition
    13. The Moore-Penrose Pseudoinverse
    14. The Trace Operator
    15. The Determinant
    16. Example: Principal Components Analysis
    17. Probability and Information Theory
    18. Why Probability?
    19. Random Variables
    20. Probability Distributions
    21. Marginal Probability
    22. Conditional Probability
    23. The Chain Rule of Conditional Probabilities
    24. Independence and Conditional Independence
    25. Expectation, Variance and Covariance
    26. Common Probability Distributions
    27. Useful Properties of Common Functions
    28. Bayes’ Rule
    29. Technical Details of Continuous Variables
    30. Information Theory
    31. Structured Probabilistic Models
    32. Numerical Computation
    33. Overflow and Underflow
    34. Poor Conditioning
    35. Gradient-Based Optimization
    36. Constrained Optimization
    37. Example: Linear Least Squares
    38. Machine Learning Basics
    39. Learning Algorithms
    40. Capacity, Overfitting and Underfitting
    41. Hyperparameters and Validation Sets
    42. Estimators, Bias and Variance
    43. Maximum Likelihood Estimation
    44. Bayesian Statistics
    45. Supervised Learning Algorithms
    46. Unsupervised Learning Algorithms
    47. Stochastic Gradient Descent
    48. Building a Machine Learning Algorithm
    49. Challenges Motivating Deep Learning
    50. Deep Networks: Modern Practices
    51. Deep Feedforward Networks
    52. Example: Learning XOR
    53. Gradient-Based Learning
    54. Hidden Units
    55. Architecture Design
    56. Back-Propagation and Other Differentiation Algorithms
    57. Historical Notes
    58. Regularization for Deep Learning
    59. Parameter Norm Penalties
    60. Norm Penalties as Constrained Optimization
    61. Regularization and Under-Constrained Problems
    62. Dataset Augmentation
    63. Noise Robustness
    64. Semi-Supervised Learning
    65. Multitask Learning
    66. Early Stopping
    67. Parameter Tying and Parameter Sharing
    68. Sparse Representations
    69. Bagging and Other Ensemble Methods
    70. Dropout
    71. Adversarial Training
    72. Tangent Distance, Tangent Prop and Manifold Tangent Classifier
    73. Optimization for Training Deep Models
    74. How Learning Differs from Pure Optimization
    75. Challenges in Neural Network Optimization
    76. Basic Algorithms
    77. Parameter Initialization Strategies
    78. Algorithms with Adaptive Learning Rates
    79. Approximate Second-Order Methods
    80. Optimization Strategies and Meta-Algorithms
    81. Convolutional Networks
    82. The Convolution Operation
    83. Motivation
    84. Pooling
    85. Convolution and Pooling as an Infinitely Strong Prior
    86. Variants of the Basic Convolution Function
    87. Structured Outputs
    88. Data Types
    89. Efficient Convolution Algorithms
    90. Random or Unsupervised Features
    91. The Neuroscientific Basis for Convolutional Networks
    92. Convolutional Networks and the History of Deep Learning
    93. Sequence Modeling: Recurrentand Recursive Nets
    94. Unfolding Computational Graphs
    95. Recurrent Neural Networks
    96. Bidirectional RNNs
    97. Encoder-Decoder Sequence-to-Sequence Architectures
    98. Deep Recurrent Networks
    99. Recursive Neural Networks
    100. The Challenge of Long-Term Dependencies
    101. Echo State Networks
    102. Leaky Units and Other Strategies for MultipleTime Scales
    103. The Long Short-Term Memory and Other Gated RNNs
    104. Optimization for Long-Term Dependencies
    105. Explicit Memory
    106. Practical Methodology
    107. Performance Metrics
    108. Default Baseline Models
    109. Determining Whether to Gather More Data
    110. Selecting Hyperparameters
    111. Debugging Strategies
    112. Example: Multi-Digit Number Recognition
    113. Applications
    114. Large-Scale Deep Learning
    115. Computer Vision
    116. Speech Recognition
    117. Natural Language Processing
    118. Other Applications
    119. Deep Learning Research
    120. Linear Factor Models
    121. Probabilistic PCA and Factor Analysis
    122. Independent Component Analysis (ICA)
    123. Slow Feature Analysis
    124. Sparse Coding
    125. Manifold Interpretation of PCA
    126. Autoencoders
    127. Undercomplete Autoencoders
    128. Regularized Autoencoders
    129. Representational Power, Layer Size and Depth
    130. Stochastic Encoders and Decoders
    131. Denoising Autoencoders
    132. Learning Manifolds with Autoencoders
    133. Contractive Autoencoders
    134. Predictive Sparse Decomposition
    135. Applications of Autoencoders
    136. Representation Learning
    137. Greedy Layer-Wise Unsupervised Pretraining
    138. Transfer Learning and Domain Adaptation
    139. Semi-Supervised Disentangling of Causal Factors
    140. Distributed Representation
    141. Exponential Gains from Depth
    142. Providing Clues to Discover Underlying Causes
    143. Structured Probabilistic Models for Deep Learning
    144. The Challenge of Unstructured Modeling
    145. Using Graphs to Describe Model Structure
    146. Sampling from Graphical Models
    147. Advantages of Structured Modeling
    148. Learning about Dependencies
    149. Inference and Approximate Inference
    150. The Deep Learning Approach to Structured Probabilistic Models
    151. Monte Carlo Methods
    152. Sampling and Monte Carlo Methods
    153. Importance Sampling
    154. Markov Chain Monte Carlo Methods
    155. Gibbs Sampling
    156. The Challenge of Mixing between Separated Modes
    157. Confronting the Partition Function
    158. The Log-Likelihood Gradient
    159. Stochastic Maximum Likelihood and Contrastive Divergence
    160. Pseudolikelihood
    161. Score Matching and Ratio Matching
    162. Denoising Score Matching
    163. Noise-Contrastive Estimation
    164. Estimating the Partition Function
    165. Approximate Inference
    166. Inference as Optimization
    167. Expectation Maximization
    168. MAP Inference and Sparse Coding
    169. Variational Inference and Learning
    170. Learned Approximate Inference
    171. Deep Generative Models
    172. Boltzmann Machines
    173. Restricted Boltzmann Machines
    174. Deep Belief Networks
    175. Deep Boltzmann Machines
    176. Boltzmann Machines for Real-Valued Data
    177. Convolutional Boltzmann Machines
    178. Boltzmann Machines for Structured or Sequential Outputs
    179. Other Boltzmann Machines
    180. Back-Propagation through Random Operations
    181. Directed Generative Nets
    182. Drawing Samples from Autoencoders
    183. Generative Stochastic Networks
    184. Other Generation Schemes
    185. Evaluating Generative Models
    186. Conclusion
    187. Bibliography
    188. Index

People also search for Deep Learning 1st Edition:

deep learning foundations and concepts 1st ed 2024 edition

deep learning for vision systems 1st edition

deep learning with python second edition pdf github

deep learning with python second edition 2nd edition

Reviews

There are no reviews yet.

Be the first to review “Deep Learning 1st Edition by Ian Goodfellow, Yoshua Bengio, Aaron Courville ISBN 9780262337373 0262337371”