Steven Edwards Profile picture
16 Jan
Time for #PapersThatMakeYouGoHmmm! A weekly summary of new ML papers from arXiv that make me think one or more of:

1. That looks useful!
2. That's an interesting approach!
3. A business could be built around this!
4. How did they do that?!
Dynamics of contentment

sciencewise.info/bookmarks/2101…
Scared into Action: How Partisanship and Fear are Associated with Reactions to Public Health Directives

sciencewise.info/bookmarks/2101…
Read 224 tweets
10 Jan
Time for #PapersThatMakeYouGoHmmm! A weekly summary of new ML papers from arXiv that make me think one or more of:

1. That looks useful!
2. That's an interesting approach!
3. A business could be built around this!
4. How did they do that?!
Argument Schemes and Dialogue for Explainable Planning

sciencewise.info/bookmarks/2101…
Neural Fitted Q Iteration based Optimal Bidding Strategy in Real Time Reactive Power Market_1

sciencewise.info/bookmarks/2101…
Read 173 tweets
3 Jan
Time for #PapersThatMakeYouGoHmmm! A weekly summary of new ML papers from arXiv that make me think one or more of:

1. That looks useful!
2. That's an interesting approach!
3. A business could be built around this!
4. How did they do that?!
Limitations of Deep Neural Networks: a discussion of G. Marcus' critical appraisal of deep learning

sciencewise.info/bookmarks/2012…
A Review into Data Science and Its Approaches in Mechanical Engineering

sciencewise.info/bookmarks/2012…
Read 166 tweets
26 Dec 20
Time for #PapersThatMakeYouGoHmmm! A weekly summary of new ML papers from arXiv that make me think one or more of:

1. That looks useful!
2. That's an interesting approach!
3. A business could be built around this!
4. How did they do that?!
Leveraging GPT-2 for Classifying Spam Reviews with Limited Labeled Data via Adversarial Training

sciencewise.info/bookmarks/2012…
Adaptive Summaries: A Personalized Concept-based Summarization Approach by Learning from Users' Feedback

sciencewise.info/bookmarks/2012…
Read 154 tweets
26 Dec 20
I'm imagining a sci-fi world that incorporates several fully-realized AI implementations while preparing this week's #PapersThatMakeYouGoHmmm list.

Several are potential #WritingPrompt(s) for #screenwriters.

There is so much potential to build a better world. #BuildBackBetter
This one, for example, brings to mind a doctor searching a Google-like engine based on caption similarity. The results include a summary of patient outcomes, pro and con.

This one a #BostonLegal-like episode with William Shatner finding a loophole in an AI's legal argument.

Read 13 tweets
28 Nov 20
Time for #PapersThatMakeYouGoHmmm! A weekly summary of new ML papers from arXiv that make me think one or more of:

1. That looks useful!
2. That's an interesting approach!
3. A business could be built around this!
4. How did they do that?!
Analyzing the Machine Learning Conference Review Process

sciencewise.info/bookmarks/2011…
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation

sciencewise.info/bookmarks/2011…
Read 177 tweets