Главная
Study mode:
on
1
Intro
2
Talk Outline
3
What is Machine Learning?
4
The Hierarchy of Artificial Intelligence
5
Machine Learning Taxonomy
6
ML Representations
7
Machine Learning vs. Traditional Programming
8
When do We Need Machine Learning?
9
The Computational Learning Process
10
Supervised ML Applied to Image Classificatio
11
The Five Elements of the Learning Process
12
Feature Engineering for "Canonical" Machine Learnin
13
"Canonical" ML Image Classification
14
Shortcomings of Traditional ML Techniques
15
The Advent of Deep Learning
16
Neurons: The Building Blocks of Rich Features
17
Neural Networks for Rich Embeddings
18
Automated Feature Discovery
19
How Can a Model Learn from Deep Embedding
20
CNN-Accuracy
21
Deep Learning Advantages and Drawbacks
22
Mining Software Repositories
23
Automation in Software Engineering Research
24
Systematic Literature Review
25
SLR Search Process
26
Publication Distribution By Venue
27
Data Processing Techniques by SE Task
28
DL4SE Neural Network Architectures
29
DLUSE Techniques to Combat Overfitting
30
DL4SE Benchmarks
31
Consideration of Occam's Razor
32
Non-Reproducibility Factors
33
Resulting Guidelines
34
Future Research Directions in DL4SE (cont'd)
35
Ethical and Social Considerations of DL4SE
36
HCI Aspects of Al-Assisted Developer Tools
37
New Application Areas and Data-Sources
38
Combining Empirical Knowledge with Deep Learning
39
Software 1.0 vs. Software 2.0
40
Software 2.0 = DL-based systems
41
Optimization by Gradient Descent to Find The Progra
42
Real-world DL-based System (Software 2.0)
43
The Transition to Software 2.0
44
Traditional SE Development vs. DL Developmer
45
Challenges: Software Development for DL
46
Challenges: Software Maintenance for DL
47
Challenges: Testing for DL
48
Challenges: Debugging for DL
49
Challenges: DL Deployment
50
What are the Next Steps?
Description:
Explore the intersection of deep learning and software engineering in this comprehensive ACM SIGSOFT webinar. Delve into the current state of Deep Learning for Software Engineering (DL4SE) research, examining its applications across various tasks like code suggestion, program repair, and synthesis. Analyze the use of different software artifacts and deep learning architectures, and confront pressing challenges in the field. Gain insights into promising future directions and opportunities for impactful, open, and reproducible research in the DL4SE community. Learn about the transition from traditional software engineering to DL-based systems (Software 2.0) and the associated challenges in development, maintenance, testing, debugging, and deployment. Discover how deep learning is revolutionizing software engineering practices and shaping the future of the field.

Deep Learning and Software Engineering - A Retrospective and Paths Forward

Association for Computing Machinery (ACM)
Add to list
#Computer Science #Deep Learning #Machine Learning #Artificial Intelligence #Neural Networks #Software Engineering #Feature Engineering
0:00 / 0:00
1 of 50

Intro