{Psychiatric, causal, psychometric} AI. Assistant prof @MGHPrecisionPsy @MGHPsychiatry MGH-Biostatistics @HarvardMed. @UCBerkeley biostat PhD
Boston, MA
Joined August 2007
- Tweets4.8K
- Following4.1K
- Followers1.4K
- Likes31K
Chris Kennedy retweeted
Realized I wrote this exactly 8 years ago
When you go about testing everyone for everything, you don’t create a world of healthy people; you create a nightmare where everyone is sick.
blogs.bmj.com/bmj/2018/06/19…
Chris Kennedy retweeted
I don't know why you need this information, but this is the aerodynamics of a beaver
Chris Kennedy retweeted
Our overview of and guidance for performance measures to evaluate medical AI is finally out!
- Stop bashing AUROC
- Calibration + clinical utility are key
- Plot risk distributions
- Classification measures are improper
thelancet.com/journals/landi…
Chris Kennedy retweeted
Incredibly, even Hinton's recent 2025 article [5] fails to cite Ivakhnenko & Lapa, the fathers of deep learning (1965) [1-3][6-10]. @geoffreyhinton claims [5] that his 1985 "Boltzmann machines" (BMs) [11] (actually 1975 Sherrington-Kirkpatrick models [6]) "are no longer used" but "were historically important" because "in the 1980s, they demonstrated that it was possible to learn appropriate weights for hidden neurons using only locally available information WITHOUT requiring a biologically implausible backward pass."
That's ridiculous. This had already been demonstrated 2 decades earlier in the 1960s in Ukraine [1-3]. Ivakhnenko's 1971 paper [3] described a deep learning network with 8 layers and layer-wise training. This depth is comparable to the depth of Hinton's BM-based 2006 "deep belief networks" with layer-wise training [4], published 35 years later without comparison to the original work [1-3] - done when compute was millions of times more expensive.
And indeed, over half a century ago, Ivakhnenko's net learned appropriate weights for hidden neurons WITHOUT requiring a biologically implausible backward pass!
Hinton & Sejnowski & co-workers have repeatedly plagiarized Ivakhnenko and others, and failed to rectify this in later surveys [6-8].
Crazy fact: today (Fri 5 Dec 2025), the inaugural so-called "Sejnowksi-Hinton Prize" will be handed out at NeurIPS 2025 for a related paper on learning without exact backpropagation [12] which also did not mention the original work on deep learning without backward pass [1-3].
What happened to peer review and scientific honesty?
REFERENCES
[1] Ivakhnenko, A. G. and Lapa, V. G. (1965). Cybernetic Predicting Devices. CCM Information Corporation. First working Deep Learners with many layers, learning internal representations.
[2] Ivakhnenko, Alexey Grigorevich. The group method of data of handling; a rival of the method of stochastic approximation. Soviet Automatic Control 13 (1968): 43-55.
[3] Ivakhnenko, A. G. (1971). Polynomial theory of complex systems. IEEE Transactions on Systems, Man and Cybernetics, (4):364-378.
[4] G. E. Hinton, R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, Vol. 313. no. 5786, pp. 504-507, 2006.
[5] G. Hinton. Nobel Lecture: Boltzmann machines. Rev. Mod. Phys. 97, 030502, 25 August 2025.
[6] J.S. A Nobel Prize for Plagiarism. Technical Report IDSIA-24-24 (2024, updated 2025).
[7] J.S. How 3 Turing awardees republished key methods and ideas whose creators they failed to credit. Technical Report IDSIA-23-23, Dec 2023.
[8] J.S. (2025). Who invented deep learning? Technical Note IDSIA-16-25.
[9] J.S. (2015). Deep learning in neural networks: An overview. Neural Networks, 61, 85-117. Got the first Best Paper Award ever issued by the journal Neural Networks, founded in 1988.
[10] J.S. Annotated History of Modern AI and Deep Learning. Technical Report IDSIA-22-22, 2022, arXiv:2212.11279.
[11] D. Ackley, G. Hinton, T. Sejnowski (1985). A Learning Algorithm for Boltzmann Machines. Cognitive Science, 9(1):147-169.
[12] T. P. Lillicrap, D. Cownden, D. B. Tweed, C. J. Akerman. Random synaptic feedback weights support error backpropagation for deep learning. Nature Communications vol. 7, 13276 (2016).
The #NobelPrize in Physics 2024 for Hopfield & Hinton turns out to be a Nobel Prize for plagiarism. They republished methodologies developed in #Ukraine and #Japan by Ivakhnenko and Amari in the 1960s & 1970s, as well as other techniques, without citing the original inventors. None of the important algorithms for modern AI were created by Hopfield & Hinton.
Today I am releasing a detailed tech report on this [NOB]: people.idsia.ch/~juergen/phy…
Of course, I had it checked by neural network pioneers and AI experts to make sure it was unassailable.
Is it now acceptable for me to direct young Ph.D. students to read old papers and rewrite and resubmit them as if they were their own works? Whatever the intention, this award says that, yes, that is perfectly fine.
Some people have lost their titles or jobs due to plagiarism, e.g., Harvard's former president [PLAG7]. But after this Nobel Prize, how can advisors now continue to tell their students that they should avoid plagiarism at all costs?
It is well known that plagiarism can be either "unintentional" or "intentional or reckless" [PLAG1-6], and the more innocent of the two may very well be partially the case here. But science has a well-established way of dealing with "multiple discovery" and plagiarism - be it unintentional [PLAG1-6][CONN21] or not [FAKE,FAKE2] - based on facts such as time stamps of publications and patents. The deontology of science requires that unintentional plagiarists correct their publications through errata and then credit the original sources properly in the future. The awardees didn't; instead the awardees kept collecting citations for inventions of other researchers [NOB][DLP]. Doesn't this behaviour turn even unintentional plagiarism [PLAG1-6] into an intentional form [FAKE2]?
I am really concerned about the message this sends to all these young students out there.
REFERENCES
[NOB] J. Schmidhuber (2024). A Nobel Prize for Plagiarism. Technical Report IDSIA-24-24. people.idsia.ch/~juergen/phy…
[NOB+] Tweet: the #NobelPrize in Physics 2024 for Hopfield & Hinton rewards plagiarism and incorrect attribution in computer science. It's mostly about Amari's "Hopfield network" and the "Boltzmann Machine." xitter.cf/SchmidhuberAI/status/1… (1/7th as popular as the original announcement by the Nobel Foundation)
[DLP] J. Schmidhuber (2023). How 3 Turing awardees republished key methods and ideas whose creators they failed to credit. Technical Report IDSIA-23-23, Swiss AI Lab IDSIA, 14 Dec 2023. people.idsia.ch/~juergen/ai-…
[DLP+] Tweet for [DLP]: xitter.cf/SchmidhuberAI/status/1…
[PLAG1] Oxford's guide to types of plagiarism (2021). Quote: "Plagiarism may be intentional or reckless, or unintentional." web.archive.org/web/20211227…
[PLAG2] Jackson State Community College (2022). Unintentional Plagiarism.
[PLAG3] R. L. Foster. Avoiding Unintentional Plagiarism. Journal for Specialists in Pediatric Nursing; Hoboken Vol. 12, Iss. 1, 2007.
[PLAG4] N. Das. Intentional or unintentional, it is never alright to plagiarize: A note on how Indian universities are advised to handle plagiarism. Perspect Clin Res 9:56-7, 2018.
[PLAG5] InfoSci-OnDemand (2023). What is Unintentional Plagiarism?
[PLAG6] Copyrighted.com (2022). How to Avoid Accidental and Unintentional Plagiarism (2023). Copy in the Internet Archive. Quote: "May it be accidental or intentional, plagiarism is still plagiarism."
[PLAG7] Cornell Review, 2024. Harvard president resigns in plagiarism scandal. 6 January 2024.
[FAKE] H. Hopf, A. Krief, G. Mehta, S. A. Matlin. Fake science and the knowledge crisis: ignorance can be fatal. Royal Society Open Science, May 2019. Quote: "Scientists must be willing to speak out when they see false information being presented in social media, traditional print or broadcast press" and "must speak out against false information and fake science in circulation and forcefully contradict public figures who promote it."
[FAKE2] L. Stenflo. Intelligent plagiarists are the most dangerous. Nature, vol. 427, p. 777 (Feb 2004). Quote: "What is worse, in my opinion, ..., are cases where scientists rewrite previous findings in different words, purposely hiding the sources of their ideas, and then during subsequent years forcefully claim that they have discovered new phenomena."
Chris Kennedy retweeted
New @APA article on precision mental health care featuring some of our recent work using ML algorithms to improve clinical suicide risk assessment for predicting future suicide attempts, and incredible ongoing work by many others! apa.org/monitor/2025/09/pers…
Chris Kennedy retweeted
Psychological science is under attack.
From funding cuts to political interference, the integrity of behavioral science—and the well-being of millions—are on the line. But this summer, we're fighting back.
Join the #StandUpForScience campaign 👇
🔗 act.standupforscience.net/ev…
Chris Kennedy retweeted
Some people today are discouraging others from learning programming on the grounds AI will automate it. This advice will be seen as some of the worst career advice ever given. I disagree with the Turing Award and Nobel prize winner who wrote, “It is far more likely that the programming occupation will become extinct [...] than that it will become all-powerful. More and more, computers will program themselves.” Statements discouraging people from learning to code are harmful!
In the 1960s, when programming moved from punchcards (where a programmer had to laboriously make holes in physical cards to write code character by character) to keyboards with terminals, programming became easier. And that made it a better time than before to begin programming. Yet it was in this era that Nobel laureate Herb Simon wrote the words quoted in the first paragraph. Today’s arguments not to learn to code continue to echo his comment.
As coding becomes easier, more people should code, not fewer!
Over the past few decades, as programming has moved from assembly language to higher-level languages like C, from desktop to cloud, from raw text editors to IDEs to AI assisted coding where sometimes one barely even looks at the generated code (which some coders recently started to call vibe coding), it is getting easier with each step.
I wrote previously that I see tech-savvy people coordinating AI tools to move toward being 10x professionals — individuals who have 10 times the impact of the average person in their field. I am increasingly convinced that the best way for many people to accomplish this is not to be just consumers of AI applications, but to learn enough coding to use AI-assisted coding tools effectively.
One question I’m asked most often is what someone should do who is worried about job displacement by AI. My answer is: Learn about AI and take control of it, because one of the most important skills in the future will be the ability to tell a computer exactly what you want, so it can do that for you. Coding (or getting AI to code for you) is a great way to do that.
When I was working on the course Generative AI for Everyone and needed to generate AI artwork for the background images, I worked with a collaborator who had studied art history and knew the language of art. He prompted Midjourney with terminology based on the historical style, palette, artist inspiration and so on — using the language of art — to get the result he wanted. I didn’t know this language, and my paltry attempts at prompting could not deliver as effective a result.
Similarly, scientists, analysts, marketers, recruiters, and people of a wide range of professions who understand the language of software through their knowledge of coding can tell an LLM or an AI-enabled IDE what they want much more precisely, and get much better results. As these tools are continuing to make coding easier, this is the best time yet to learn to code, to learn the language of software, and learn to make computers do exactly what you want them to do.
[Original text: deeplearning.ai/the-batch/is… ]
Chris Kennedy retweeted
Join Machine Learning for Estimating Causal Effects w/ @ashley_naimi on Aug. 6-9. Learn to use cutting-edge "double-robust" #machinelearning methods to estimate treatment effects, minimize biases, & avoid problems like the “curse of dimensionality.”
Chris Kennedy retweeted
Really excited about this paper, w/ amazing postdoc Alex Levis
awlevis.com/about/
We propose conditional potential benefit (CPB) measure, ie the improvement under optimal trt vs status quo
We describe id assumptions & propose nonparametric, robust, & efficient estimators
Chris Kennedy retweeted
My boring 2 cents on last night: read this paper by Le Pennec and @VinPons before arriving at any far-reching conclusions.
vincentpons.org/tvdebates
Chris Kennedy retweeted
“All models are wrong and yours are useless: making clinical prediction models impactful for patients” nature.com/articles/s41698-0…
Lot of great points here! You may have heard a few of these from me the past few years, particularly about using multiomics for clinical prediction – at Raleigh, NC
Chris Kennedy retweeted
🎙️ I learned a ton from @mark_vdlaan in this discussion! Some things it has me thinking more about:
🕳️ The "causal gap" -- distinguishing between the causal estimand vs the statistical estimand
🤸♀️ The benefits of considering both simple parametric and flexible candidate models
Chris Kennedy retweeted
More than 50% of the reported reasoning abilities of LLMs might not be true reasoning.
How do we evaluate models trained on the entire internet? I.e., what novel questions can we ask of something that has seen all written knowledge? Below: new eval, results, code, and paper.
Functional benchmarks are a new way to do reasoning evals. Take a popular benchmark, e.g., MATH, and manually rewrite its reasoning into code, MATH(). Run the code to get a snapshot that asks for the same reasoning but not the same question. A reasoning gap exists if a model’s performance is different on snapshots. Big question: Are current SOTA models closer to gap 0 (proper reasoning) or gap 100 (lots of memorization)?
What we find: Gaps in the range of 58% to 80% in a bunch of SOTA models. Motivates us to build Gap 0 models.
We’re releasing the paper, code, and 3 snapshots of functional MATH() today.
arxiv draft: arxiv.org/abs/2402.19450
github repo: github.com/ConsequentAI/fnev…
1/🧵
Chris Kennedy retweeted
It's time to stop making t-SNE & UMAP plots. In a new preprint w/ Tara Chari we show that while they display some correlation with the underlying high-dimension data, they don't preserve local or global structure & are misleading. They're also arbitrary.🧵biorxiv.org/content/10.1101/…
Chris Kennedy retweeted
This is a @xieyihui appreciation post
#rstats, please join me in sponsoring @xieyihui on @github
github.com/sponsors/yihui
(Context: yihui.org/en/2024/01/bye-rst…)
1/n 🧵(or shall I say 🧶)
Chris Kennedy retweeted
ICYMI: We're welcoming applications for Assist/Assoc Prof faculty position @harvardmed & @MassGeneral, Associate Director @MGHPrecisionPsy & Tommy Fuss Endowed Chair in Precision Psychiatry!
cc: @ISPGnet @AMIAinformatics @PGCgenetics @CDC_Genomics @precisionforum @APApsychiatric
Chris Kennedy retweeted
Big news! decisioncurveanalysis.org has been completely updated and revamped. Code, tutorials, guides, bibliographies, videos and more! Amazing job by @ShaunPorwal @statistishdan
Chris Kennedy retweeted
ChatGPT not best at many language tasks. It's outranked by other systems on many NLP benchmarks in current evaluation. For 77.5% of tasks examined, other systems are better than ChatGPT.
opensamizdat.com/posts/chatg…
