Deep Learning and Software Engineering - A Retrospective and Paths Forward

Deep Learning and Software Engineering - A Retrospective and Paths Forward

Association for Computing Machinery (ACM) via YouTube Direct link

Intro

1 of 50

1 of 50

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Deep Learning and Software Engineering - A Retrospective and Paths Forward

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Talk Outline
  3. 3 What is Machine Learning?
  4. 4 The Hierarchy of Artificial Intelligence
  5. 5 Machine Learning Taxonomy
  6. 6 ML Representations
  7. 7 Machine Learning vs. Traditional Programming
  8. 8 When do We Need Machine Learning?
  9. 9 The Computational Learning Process
  10. 10 Supervised ML Applied to Image Classificatio
  11. 11 The Five Elements of the Learning Process
  12. 12 Feature Engineering for "Canonical" Machine Learnin
  13. 13 "Canonical" ML Image Classification
  14. 14 Shortcomings of Traditional ML Techniques
  15. 15 The Advent of Deep Learning
  16. 16 Neurons: The Building Blocks of Rich Features
  17. 17 Neural Networks for Rich Embeddings
  18. 18 Automated Feature Discovery
  19. 19 How Can a Model Learn from Deep Embedding
  20. 20 CNN-Accuracy
  21. 21 Deep Learning Advantages and Drawbacks
  22. 22 Mining Software Repositories
  23. 23 Automation in Software Engineering Research
  24. 24 Systematic Literature Review
  25. 25 SLR Search Process
  26. 26 Publication Distribution By Venue
  27. 27 Data Processing Techniques by SE Task
  28. 28 DL4SE Neural Network Architectures
  29. 29 DLUSE Techniques to Combat Overfitting
  30. 30 DL4SE Benchmarks
  31. 31 Consideration of Occam's Razor
  32. 32 Non-Reproducibility Factors
  33. 33 Resulting Guidelines
  34. 34 Future Research Directions in DL4SE (cont'd)
  35. 35 Ethical and Social Considerations of DL4SE
  36. 36 HCI Aspects of Al-Assisted Developer Tools
  37. 37 New Application Areas and Data-Sources
  38. 38 Combining Empirical Knowledge with Deep Learning
  39. 39 Software 1.0 vs. Software 2.0
  40. 40 Software 2.0 = DL-based systems
  41. 41 Optimization by Gradient Descent to Find The Progra
  42. 42 Real-world DL-based System (Software 2.0)
  43. 43 The Transition to Software 2.0
  44. 44 Traditional SE Development vs. DL Developmer
  45. 45 Challenges: Software Development for DL
  46. 46 Challenges: Software Maintenance for DL
  47. 47 Challenges: Testing for DL
  48. 48 Challenges: Debugging for DL
  49. 49 Challenges: DL Deployment
  50. 50 What are the Next Steps?

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.