Feel free to comment with any thoughts on our latest articles, newsletters, or podcast interviews, OR suggestions for things to cover or people to interview, or any questions for The Gradient editors!
Here are links to the latest from The Gradient if you missed any of it:
Hello all! I'd really like to see some more articles about interpretability, explicability, saliency mapping etc - it's what I'm working on right now: (shameless self promotion: https://arxiv.org/abs/2103.05108) and I feel is very much of the zeitgeist at the moment. We're making more and more complex and powerful models - we need ways to understand and learn from them.
You should try to improve the audio quality more (getting rid of reverb, static noise, air conditioners). A number of online services or downloadable programs can help with this, and I don’t want to push any specific one.
Thanks for the suggestion! We actually do so already using Adobe Audition. But the results vary depending on the nature of the background noise and quality of original audio etc. We'll aim to keep improving, of course.
Hello all! I'd really like to see some more articles about interpretability, explicability, saliency mapping etc - it's what I'm working on right now: (shameless self promotion: https://arxiv.org/abs/2103.05108) and I feel is very much of the zeitgeist at the moment. We're making more and more complex and powerful models - we need ways to understand and learn from them.
Thanks for the recommendation!
You should try to improve the audio quality more (getting rid of reverb, static noise, air conditioners). A number of online services or downloadable programs can help with this, and I don’t want to push any specific one.
Thanks for the suggestion! We actually do so already using Adobe Audition. But the results vary depending on the nature of the background noise and quality of original audio etc. We'll aim to keep improving, of course.