Deep Learning Path

Neural Networks

Practical aspects of Deep Learning [2]

Optimization algorithms [2]

  • Gradient descent [2]
  • Gradient descent with momentum [2]
  • Stochastic gradient descent [4]
  • RMSprop [2]
  • Adam [2]
  • Learning rate decay [2]

Hyperparameter tuning, Batch Normalization and Programming Frameworks [2]

ML Strategy [3]

  • Orthogonalization [3]
  • Single number evaluation metric [3]
  • Satisficing and Optimizing metric [3]
  • Train/dev/test distributions [3]
  • Size of the dev and test sets [3]
  • When to change dev/test sets and metrics [3]
  • Avoidable bias [3]
  • human-level performance [3]
  • Improving model performance [3]
  • error analysis [3]
  • Training and testing on different distribution [3]
  • data mismatch [3]
  • Transfer learning [3]
  • Multi-task learning [3]
  • end-to-end deep learning [3]

Deep Learning Frameworks

References

  1. Neural Networks and Deep Learning
  2. Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
  3. Structuring Machine Learning Projects
  4. Introduction to Deep Learning