New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conclusions #370
Conclusions #370
Conversation
sections/07_conclusions.md
Outdated
its dominance over competing machine learning approaches in many of the areas | ||
reviewed here and quantitative improvements in predictive performance, deep | ||
learning has not yet qualitatively "solved" those problems that were previously | ||
"unsolved". |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is
that were previously "unsolved"
needed here? It sounds like a bit of a repetition to me.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Cut text
sections/07_conclusions.md
Outdated
finally approaching or exceeding human performance in the past year | ||
[@arxiv:1610.05256 @arxiv:1703.02136] `TODO: working on a second source for this | ||
error trajectory from a talk by Eric Horvitz`. The phenomenal improvements on | ||
benchmark datasets are undeniable, but the successes of the early 2010s did not |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe it's just me but I don't think it's overly clear what the
successes of the early 2010s
are.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good point, this is unclear. I'm thinking of the left image from https://twitter.com/amram/status/845748240033050624 However, I can't directly use it because I don't know the source, and Eric is likely too busy being the new head of MSR to reply. http://www.businessinsider.com/ibm-edges-closer-to-human-speech-recognition-2017-3 shows comparable numbers but with less granularity.
I changed this to "...are undeniable, but halving the error rates on these benchmarks did not fundamentally transform...". Still not perfect, but that's my intended message.
No one is pushing back on my conversational speech example, so I removed: TODO: this is debatable, maybe need a different example or to clarify what is meant by "conversational" speech
sections/07_conclusions.md
Outdated
fundamentally transform the domain. `TODO: this is debatable, maybe need a | ||
different example or to clarify what is meant by "conversational" speech` | ||
Widespread adoption of these technologies will requires not only improvements | ||
over baseline methods but truly "solving" the problem, in this case exceeding |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Since this is the second time you use 'solve' in this section I think the double quotes are unnecessary.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Fixed
sections/07_conclusions.md
Outdated
[@doi:10.1001/jama.2016.17216], diabetic macular edema | ||
[@doi:10.1001/jama.2016.17216], and skin lesion [@doi:10.1038/nature21056] | ||
classifiers are highly accurate and comparable to dermatologist performance in | ||
the latter case. `TODO: more imaging examples or other examples that might be at |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
comparable to dermatologist performance in the latter case
sounds too specific for this section, maybe consider something more generic like
comparable to human performance
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Agreed - reads easier.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changed to "comparable to clinician performance" to differentiate between an expert and average human, but I can reword this further if you would like
sections/07_conclusions.md
Outdated
[@doi:10.1001/jama.2016.17216], diabetic macular edema | ||
[@doi:10.1001/jama.2016.17216], and skin lesion [@doi:10.1038/nature21056] | ||
classifiers are highly accurate and comparable to dermatologist performance in | ||
the latter case. `TODO: more imaging examples or other examples that might be at |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Agree, maybe you can add #366 here?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Added it. I like the idea about using experts to review a smaller set of images where two CNNs disagree, but that may be better for the Categorize sub-section instead of expanding the conclusions.
sections/07_conclusions.md
Outdated
[@doi:10.1001/jama.2016.17216], and skin lesion [@doi:10.1038/nature21056] | ||
classifiers are highly accurate and comparable to dermatologist performance in | ||
the latter case. `TODO: more imaging examples or other examples that might be at | ||
or close to "transformative"?` In other domains, perfect accuracy will not be |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we want to argue that in some domains perfect accuracy might not even be possible? Not sure what arguments we could bring here but intuitively some complex problems (e.g: gene regulation in disease) might not be within DL reach, no matter how good the algorithm is.
Just a thought, I appreciate it's a rather subjective stance and not everyone might agree.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I agree with @enricoferrero that in some areas perfect performance may be impossible for any algorithm due to the stochastic/critical nature of biological systems. Maybe just one closing sentence to this paragraph since it's the perfect accuracy may not... paragraph. Also, I think you may want to start a new paragraph at "In other domains...".
@agitter : if you want to create an issue for this, I or @enricoferrero can likely address afterwards. Up to you on what you prefer.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I completely agree with this sentiment. I reworked this slightly; see if it needs more editing and a new issue. My intention is to keep the two examples where deep learning is closer to practical impact (medical imaging and chemical screening) together. Then I split a new paragraph for the more negative examples.
sections/07_conclusions.md
Outdated
approaches that would be infeasible with other machine learning techniques. | ||
Unsupervised methods are currently less-developed than their supervised | ||
counterparts, making them an attractive target for future research in this | ||
domain. `TODO: still working on a strong closing line` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I feel this sentence on unsupervised learning could be expanded a little bit. Maybe we could argue that since a lot of biomedical data is unlabelled and labelling has to be done manually, accurate deep unsupervised methods could also be transformative in high impact fields such as patient stratification for precision medicine approaches.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Updated per @cgreene's suggestion below
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@agitter Great section, thanks. I've left a few minor comments here and there.
@enricoferrero thanks for these comments. These are excellent suggestions, and I'll make point-by-point responses and text updates, hopefully tonight. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I had a few thoughts. I also had a couple points where I need more clarity to provide a helpful review. I love where this is going though! I suggested a potential final sentence.
sections/07_conclusions.md
Outdated
[@doi:10.1001/jama.2016.17216], and skin lesion [@doi:10.1038/nature21056] | ||
classifiers are highly accurate and comparable to dermatologist performance in | ||
the latter case. `TODO: more imaging examples or other examples that might be at | ||
or close to "transformative"?` In other domains, perfect accuracy will not be |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I agree with @enricoferrero that in some areas perfect performance may be impossible for any algorithm due to the stochastic/critical nature of biological systems. Maybe just one closing sentence to this paragraph since it's the perfect accuracy may not... paragraph. Also, I think you may want to start a new paragraph at "In other domains...".
@agitter : if you want to create an issue for this, I or @enricoferrero can likely address afterwards. Up to you on what you prefer.
sections/07_conclusions.md
Outdated
For example, in chemical screening for drug discovery, a deep learning system | ||
that successfully identifies dozens or hundreds of target-specific, active | ||
small molecules from a massive search space would have immense practical value | ||
even if its overall precision is modest. Conversely, the most challenging tasks |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would need some clarification here to decide if this should be elaborated on. Why are these potentially the most challenging? I guess I am missing the rationale for this statement.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Perhaps I mean to say that errors may be magnified in some cases if we rely on predictions for some secondary task. For instance, suppose I rely on predictions of TF binding from a neural net to predict TF binding and then use those genome-wide predictions to model gene expression. I'll need to be more accurate than if I were going to use those predictions to follow up on a few interesting or high-confidence binding sites.
sections/07_conclusions.md
Outdated
challenges beyond improving training and predictive accuracy, such as preserving | ||
patient privacy and interpreting models. Ongoing research has begun to address | ||
these problems and shown they are not insurmountable. Deep learning offers the | ||
flexibility to model data in its most natural form, spurring creative modeling |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What do you mean by "most natural form" here?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm thinking of things like graph convolutional networks that allow one to work directly on a molecular graph for chemical modeling. Previously, pre-computed lossy feature representations are more common when using other machine learning approaches. I could probably come up with examples in other domains as well.
sections/07_conclusions.md
Outdated
these problems and shown they are not insurmountable. Deep learning offers the | ||
flexibility to model data in its most natural form, spurring creative modeling | ||
approaches that would be infeasible with other machine learning techniques. | ||
Unsupervised methods are currently less-developed than their supervised |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Unsupervised methods are currently less-developed than their supervised counterparts, but they may have the most potential. When deep learning algorithms can summarize very large collections of input data into interpretable models that spur scientists to ask questions that we didn't know to ask, it will be clear that deep learning has transformed biology and medicine.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
@cgreene thanks, I'll be able to clarify these parts in my next pass. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good - my comments should be taken largely as suggestions at to how to polish it.
sections/07_conclusions.md
Outdated
@@ -1,15 +1,60 @@ | |||
## Conclusions | |||
|
|||
Final thoughts and future outlook here. The Discussion will give an overview | |||
and the Conclusion will provide a short, punchy take home message. | |||
Deep learning-based methods now represent the state of the art in a diverse |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm a little uncomfortable about "state of the art" in that it's making an assertion that deep learning is the state of the art. Perhaps instead say "deep learning now matches or suprasses previous state of the art"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, that's better
sections/07_conclusions.md
Outdated
its transformative potential or induced a strategic inflection point. Despite | ||
its dominance over competing machine learning approaches in many of the areas | ||
reviewed here and quantitative improvements in predictive performance, deep | ||
learning has not yet qualitatively "solved" those problems that were previously |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
instead of "qualitatively" maybe "definitively" / "inarguably"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changed
sections/07_conclusions.md
Outdated
human-level performance, as well as convincing users to embrace the technology | ||
[@tag:Speech_recognition]. We see parallels to the healthcare domain, where | ||
achieving the full potential of deep learning will require outstanding | ||
predictive performance as well as adoption by biologists and clinicians. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
maybe "acceptance and adoption"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changed
sections/07_conclusions.md
Outdated
[@doi:10.1001/jama.2016.17216], diabetic macular edema | ||
[@doi:10.1001/jama.2016.17216], and skin lesion [@doi:10.1038/nature21056] | ||
classifiers are highly accurate and comparable to dermatologist performance in | ||
the latter case. `TODO: more imaging examples or other examples that might be at |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Agreed - reads easier.
sections/07_conclusions.md
Outdated
classifiers are highly accurate and comparable to dermatologist performance in | ||
the latter case. `TODO: more imaging examples or other examples that might be at | ||
or close to "transformative"?` In other domains, perfect accuracy will not be | ||
required because deep learning will be used primarily to prioritize experiments. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I like this point a lot: imperfect solutions can be damn useful. Perhaps it needs to be broken out to a separate paragraph to emphasis? I'm thinking there's a lot of value in "assisted discovery" and highlighting areas for further investigation. Conversely, this could blow out into far too long a discussion.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Glad you like it. I made a separate paragraph and added an example from #366. We could probably add at least one more to make the point stronger if you have ideas.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I should add, I'm somewhat concerned the false negatives in the deep learning-assisted strategy proposed in #366.
sections/07_conclusions.md
Outdated
decision-making, especially in the clinic. `TODO: elaborate more on this idea | ||
or split in a new paragraph?` | ||
|
||
Even if deep learning in biology and healthcare is not yet transformative today, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
... and it's early days yet, full potential not explored, deep learning still evolving, yadda yadda yadda
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Added a line
Thanks again @enricoferrero @cgreene @agapow. I updated the text or commented in response to all feedback above. There are still some open questions we can resolve before merging, mostly in response to @cgreene. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good - one small language suggestion
sections/07_conclusions.md
Outdated
"unsolved". | ||
Deep learning-based methods now matches or surpasses the previous state of the | ||
art in a diverse array of tasks in patient and disease categorization, | ||
fundamental biological study, genomics, and treatment development. We return to |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
"Returning to our central question": less passive
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, that's better. I changed it.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
One minor change then LGTM 👍 . Very nice!
sections/07_conclusions.md
Outdated
@@ -1,15 +1,70 @@ | |||
## Conclusions | |||
|
|||
Final thoughts and future outlook here. The Discussion will give an overview | |||
and the Conclusion will provide a short, punchy take home message. | |||
Deep learning-based methods now matches or surpasses the previous state of the |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
subject/verb agreement
Made the last change from @cgreene and addressed a couple TODOs. Merging now. I added this example to clarify one of my remarks: "As an example, errors in a predicted protein contact map could be amplified if that contact map is used directly for 3D structure prediction." @j3xugit, is this statement correct in your opinion? |
This build is based on 2dfa08a. This commit was created by the following Travis CI build and job: https://travis-ci.org/greenelab/deep-review/builds/228757316 https://travis-ci.org/greenelab/deep-review/jobs/228757317 [ci skip] The full commit message that triggered this build is copied below: Conclusions (#370) * Initial draft of conclusions * Respond to feedback * Rephrasing * Address TODOs and grammar * Minor rewording
This build is based on 2dfa08a. This commit was created by the following Travis CI build and job: https://travis-ci.org/greenelab/deep-review/builds/228757316 https://travis-ci.org/greenelab/deep-review/jobs/228757317 [ci skip] The full commit message that triggered this build is copied below: Conclusions (#370) * Initial draft of conclusions * Respond to feedback * Rephrasing * Address TODOs and grammar * Minor rewording
In fact, we can directly use predicted contact maps to predict 3D
structures and for many proteins we indeed produce very good 3D modeling.
The prediction error of an individual contact may be big, but when multiple
predicted contacts are used together for 3D structure modeling, the impact
of an individual contact is usually reduced instead of amplified.
By the way, I believe that the change of ab initio folding is
transformative in the past few years due to 1) significantly improved
co-evolution analysis; and 2) significantly improved contact prediction by
deep learning.
…On Thu, May 4, 2017 at 9:16 AM, Anthony Gitter ***@***.***> wrote:
Made the last change from @cgreene <https://github.com/cgreene> and
addressed a couple TODOs. Merging now.
I added this example to clarify one of my remarks: "As an example, errors
in a predicted protein contact map could be amplified if that contact map
is used directly for 3D structure prediction." @j3xugit
<https://github.com/j3xugit>, is this statement correct in your opinion?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#370 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AKR63opN4qoO1559KyTxbWAMZQ2wZR0oks5r2d2mgaJpZM4NNtGm>
.
--
_________________________________________
Professor
Toyota Technological Institute at Chicago
6045 S. Kenwood Ave.
Chicago, IL 60637
fax: 773 834 2557, Google Voice: 773 359 3721
http://ttic.uchicago.edu/~jinbo/
|
@cgreene see if you agree with the position I took, and feel welcome to tear down this entire section if you have a different stance.
This will be one focal point of the review, so others can provide feedback as well.