Sources

5 Key Challenges in Machine Learning Development

  1. K. Leetaru. "We Must Recognize Just How Brittle And Unpredictable Today's Correlative Deep Learning AI Is." Forbes, 2019
  2. J .Brownlee. "How to Choose Loss Functions When Training Deep Learning Neural Networks." Machine Learning Mastery, 2020
  3. J. Wesner. "MAE and RMSE — Which Metric is Better?" Human In A Machine World, 2016
  4. "Learning rate scheduler." TensorFlow, 2020
  5. A. Rosebrock. "Keras learning rate schedules and decay." PyImageSearch, 2019
  6. J .Brownlee. "Why Do I Get Different Results Each Time in Machine Learning?" Machine Learning Mastery, 2020
  7. E. Jang. "Why Randomness is Important for Deep Learning." Eric Jang Blog, 2016
  8. Z. Qi et al. "Impacts of Dirty Data: an Experimental Evaluation." ResearchGate, 2018
  9. J. Picado. "Learning Over Dirty Data Without Cleaning." Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, 2020
  10. J .Brownlee. "How to Use Weight Decay to Reduce Overfitting of Neural Network in Keras." Machine Learning Mastery, 2020