Discover and read the best of Twitter Threads about #ml

Most recents (24)

1/ After a year of work, our paper on mRNA Degradation is finally out!

paper: arxiv.org/abs/2110.07531
code: github.com/eternagame/Kag…
2/ A year ago I was approached with a unique and exciting opportunity: I was asked to help out with setting a Kaggle Open Vaccine competition, where the goal would be to come up with a Machine Learning model for the stability of RNA molecules.
3/ This is of a pressing importance for the development of the mRNA vaccines. The task seemed a bit daunting, since I have had no prior experience with RNA or Biophysics, but wanted to help out any way I could.
Read 8 tweets
@cori_crider @nyunt_pye @AdaLovelaceInst @ImogenParker @Foxglovelegal Hi @cori_crider!100% of your NHS cases conceding pre-permission just shows they dont have the resources to engage in a long drawn out legal battle.

There are so many uses of machine learning& automated allocation in social commissioning models in local govts across the UK 1/12
@cori_crider @nyunt_pye @AdaLovelaceInst @ImogenParker @Foxglovelegal They use it to speak to NHS, allocate resources& predict need for services-built by private analytics consultancies

Esp in integrated planning systems bridging local authorities, NHS& other agencies with responsibilities for pub health, #ML is used to curate info for people 2/12
@cori_crider @nyunt_pye @AdaLovelaceInst @ImogenParker @Foxglovelegal Once these systems are in place I’m sure it is possible to take a risk model developed in social care to another department within the same public organisation for debt recovery 3/12
Read 13 tweets
Our paper dropped: Performance Metrics for Comparative Analysis of Clinical Risk Prediction Models Employing Machine Learning. We show 'commonly reported metrics may not have sufficient sensitivity to identify improvement of
#ML models…’ @CircOutcomes ahajournals.org/doi/abs/10.116…
@CircOutcomes Risk models are ubiquitous now. In this paper, we 'propose the use of a comprehensive list of performance metrics for reporting and comparing clinical risk prediction models.’ Time to expand the metrics. @CircOutcomes ahajournals.org/doi/abs/10.116… @YaleMed @YaleCardiology @AHAScience
@CircOutcomes @YaleMed @YaleCardiology @AHAScience We review a wide range of options for assessing the performance of risk models and demonstrate the neccessity of a comprehensive view in any evaluation. Paper was led by Chenxi Huang. Also with @jbmortazavi; SL Normand; @jspertus @CesarCaraballoC @Dr_BowTie65 @DrJRums
Read 6 tweets
💛 Machine Learning from Scratch for beginners !!

A Thread 🧵 👇
#100DaysOfCode #Ml #MachineLearning #CodeNewBie #AI
🔹What is Machine Learning ?

Machine Learning is a growing technology which enables computer to learn automatically from past data . It uses various algorithms for building mathematical models and making predictions using historical data or information . Image
🔹 What is a model in ML ?

A machine learning model is a file that has been trained to recognize certain types of patterns. You train a model over a set of data, providing it an algorithm that it can use to reason over and learn from those data.
Read 17 tweets
My favorite #Youtube channels to stay updated with #ML research:

- Yannic Kilcher @ykilcher
- AI Epiphany by @gordic_aleksa
- AI Coffee Break with Letitia @AICoffeeBreak
- Two Minutes Papers @twominutepapers
- Arxiv Insights by @xsteenbrugge
- Henry AI Labs @labs_henry
@ykilcher @gordic_aleksa @AICoffeeBreak @twominutepapers @xsteenbrugge @labs_henry Following @zubairahmed_ai here are the links for all channels:

- Yannic Klitcher: youtube.com/channel/UCZHmQ…

- AI Epiphany:
youtube.com/channel/UCj8sh…

- AI Coffee Break with Letitia:
youtube.com/channel/UCobqg…

- Two Minutes Papers:
youtube.com/channel/UCobqg…

1/2
- Arxiv Insights
youtube.com/c/ArxivInsights

- Henry AI Labs
youtube.com/channel/UCHB9V…

2/2
Read 3 tweets
Can ethical, inclusive tech help to create a better world?

This @wef report argues that critical #technologies such as artificial intelligence (#AI) and machine learning, have already defined our world.

1/4
@AlbertoMChi @oost_marcel @SaeedBaygi #ML #BigData
Their point is that it's not the #technology, but its curation that matters. Technology for technology's sake is neither positive nor negative.

To paraphrase Tim Cook over the weekend...it's all about trust.

2/4
@jaypalter @terence_mills @KeithKeller #TimCook #BigTech Image
It's a theme I keep coming back to because there are lots of examples of "bad #tech", by which i mean "bad USES of tech".

#Facebook and #Robinhood come to mind, and there are many more.

3/4
@efipm @profgalloway @SpirosMargaris #Gamification
bit.ly/3igBrOU
Read 4 tweets
. @awscloud #reinforce // here we go…

🎙🧵

☁️ #cloud #security #devops
Adam Selipsky (CEO, AWS) up first with an opening message for @awscloud #reinforce
“Security is job ZERO at @awscloud”, Adam Selipsky. he’s referring to the fact that it is required as a baseline before building or doing anything

he goes on to say that #security is critical to AWS’ success and customer success

#cloud #devops
Read 121 tweets
Are you aware of Boston Dynamics' amazingly advanced robots?
Well @elonmusk just announced he's entering the humanoid robots game and we're all EXCITED! 🤩

Read along! (Thread)

(1/n)

#machinelearning #tesla #BostonDynamics #ElonMusk #robot #AI
@elonmusk Tesla apart from being an automaker is also popularly known for its AI capabilities. The FSD or full self driving capabilities of tesla are unmatched in the 🚗 industry!
.
(2/n)

#machinelearning #tesla #BostonDynamics #ElonMusk #robot #AI
@elonmusk Elon Musk on Thursday unveiled a humanoid robot called the Tesla Bot that runs on the same AI used by Tesla's fleet of autonomous vehicles. 🤩

(3/n)

#machinelearning #tesla #BostonDynamics #ElonMusk #robot #AI
Read 7 tweets
1/

Thread of the very best #YouTube channels and #Twitter accounts to follow for:

#AI/ #ML, #DeepLearning, #neural and all things #datascience

bit.ly/3g8pVDL

#AI #machinelearning @wiserin10 #datascience #bigdata #artificialintelligence
2/

@Analyticsindiam

Analytics India Magazine includes discussions on news, tips for the data ecosystem and a deep dive into #AI/#ML, #deeplearning and #neural networks

#YouTube subscriber count: 38k
3/

@Krishnaik06

Krish Naik is co-founder of iNeuron.ai and specialises in #machinelearning, #deeplearning, and computer vision. Krish’s #YouTube channel is a deep dive into all things #AI/#ML, perfect for beginners

YouTube subscriber count: 421k
Read 15 tweets
Quick Tweet Storm ⛈

How does AI bounding box detection work?

🧠 Learn in 30 seconds

#100DaysOfCode #CodeNewbie #MadeWithTFJS #MachineLearning #ComputerVision Image
It looks so simple when #AI does it right?

But #machinelearning doesn't give you an image, it gives you data. It's up to you to make it look simple. Image
You might think a #FrontEnd box gives you four values, and you're right, but it only gives you TWO points. From that you can infer a box to draw with #html5. Image
Read 9 tweets
#JSM2021 an exceptionally rare case of ACTUAL out of sample prediction in #MachineLearning #ML #AI: two rounds of the same health data collection by @CDCgov
@CDCgov Yulei He @cdcgov #JSM2021 RANDS 1 (fall 2015) + 2 (spring 2016): Build models on RANDS1 and compare predictions for RANDS2

ridge, lasso, elastic net, PLS, KNN, bagging, RF, GBM, XGBoost, SVM, deep learning
#JSM2021 Yulei He R-square about 30%; random forests and grad boosting reduce the prediction error by about 4%, shrinking towards the mean; standard errors are way to small (-50% than should be)
Read 4 tweets
Each week I pull ~51000 tweets on US State mentions and do sentiment analysis. Most positive state was #Maine according to an ensemble model! In the replies are the individual models.
GitHub: github.com/ghadlich/State…
#NLP #Python #ML
I analyzed the sentiment on Twitter for each state + DC from the last week using a pretrained #BERT model from #huggingface.
Which state had the most positive mentions this week? It was #Maine!
#NLP #Python #ML
I analyzed the sentiment on Twitter for each state + DC from the last week using a pretrained #VADER model from #NLTK.
Which state had the most positive mentions this week? It was #DistrictofColumbia!
#NLP #Python #ML
Read 7 tweets
Personal Services Experience (PSE)
Artificial Intelligence (AI), Machine Learning (ML) algorithms and Big Data Engines matching best services based on your Healthcare data, interest, personal nutrition recommendations etc.
#inserviss #startups #ai #ml
Check the thread 👇
With help of @inservissapp Business and entrepreneurs can focus on Quality of Services and we will take care for what is really mattering for you
#inserviss
Next 👇
Curiosity and open minding provide unstoppable progress for each generations. 
Learning in playing, keep educating in nature, create great background for everyone to learn soft & hard skills
#inserviss unlock creativity & inspirations, which resonates with your passions
Next👇
Read 6 tweets
Each week I pull ~51000 tweets on US State mentions and do sentiment analysis. Most positive state was #Utah according to an ensemble model! In the replies are the individual models.
GitHub: github.com/ghadlich/State…
#NLP #Python #ML
I analyzed the sentiment on Twitter for each state + DC from the last week using a pretrained #BERT model from #huggingface.
Which state had the most positive mentions this week? It was #Utah!
#NLP #Python #ML
I analyzed the sentiment on Twitter for each state + DC from the last week using a pretrained #VADER model from #NLTK.
Which state had the most positive mentions this week? It was #Nevada!
#NLP #Python #ML
Read 7 tweets
Next steps how to increase #vc #investments and boost #innovations as they are one of major drivers for post pandemic recovery and transition for digital economy.
Check the thread 🧵 👇

#startups #ecommerce #startup #growth #fintech #ai #ml #rpa #edtech #biotech
#Tech sector provide opportunities into #early, #growth and #late stages companies for #vc #financial #investments and #allocations capital into #startups for sustainable investments
Next👇

#fintech #innovation #ecommerce #startup #growth #ArtificialIntelligence
@dseinnovations #VC fund increase investments into #Fintech, #AI, #RPA, #Cleantech, #Agtech, #Edtech, #Marketplaces, #biotech and other #tech sectors

For #LP’s who are interested to join, please contact directly or email, DM @igorperep
#startup #innovation
Read 4 tweets
I'm really looking forward to participating in the forthcoming @markcubanai Boot Camps this Fall! I will be participating as a mentor and collaborating with @Caltech and the @AppAcademyPHS! cc @mcuban #AI #artificialintelligence #machinelearning #ML
The Mark Cuban Foundation works with local companies to host Introduction to #AI bootcamps for underserved high school (9th-12th) grade students at no cost.
the program does not have any pre-requisites or require any prior experience with coding. Students with any level of interest in technology will walk away from the @markcubanai program with a greater understanding of #AI
Read 8 tweets
🙋‍♀️ Do you know AlphaFold? It is a protein-folding AI tool developed by Deepmind 🙌

Now Deepmind has announced something astonishing! 🤯

Read along! (Thread) ⬇️

#BigData #Analytics #DataScience #AI #MachineLearning #Python #Coding #100DaysofCode #ML #ArtificialIntelligence
In December 2020, @DeepMind introduced AlphaFold which could predict the structure of proteins! 💯

This tool helped solve a 50-year grand challenge! 😮

(2/n)
@DeepMind “Protein folding is a problem I've had my eye on for more than 20 years,”
- DeepMind co-founder and CEO Demis Hassabis.

(3/n)
Read 8 tweets
Will #AI enhance care of patients?
Yes!
How?
-Improved reliability
-Atherosclerosis guided Rx
-Risk prediction
-Requires validation ✅

Proud to share my #SCCT2021 talk (1/5)
AI & ML in #YesCCT: New Frontiers in Atherosclerosis
@mirvatalasnag @HeartOTXHeartMD @DrIanWeissman
#SCCT2021 (2/5)
AI & ML in #YesCCT: New Frontiers in Atherosclerosis

-The field of #YesCCT has evolved rapidly
-Current CV risk prediction models are inadequate – can AI help?
-Average imager may read > 1 billion pixels per day
#SCCT2021 (3/5)
#AI & ML in #YesCCT: Atherosclerosis

-Be mindful of caveats, ensure validity & avoid hype
-Opportunity to improve #CCT reproducibility (in conjunction w/ education!)
-#CLARIFY - algorithm validation
-#CLARIFY– high accuracy for %stenosis

@mirvatalasnag
Read 5 tweets
Great session on Artificial Intelligence and Machine learning with session chairs @imagingmedsci, Dr. Bratt, @michael_t_lu, @ivanaisgum, Dr. Al'Aref and @DeCeccoCN at #SCCT2021!

#ICYMI - Here's a brief tweetorial from the #YesCCT session (1/7)
@mirvatalasnag @HeartOTXHeartMD
#AI & ML in #YesCCT: #SCCT2021 #Tweetorial (2/7)
1⃣: The big picture & black box by Dr. Michael Lu
-Multiple “black box” definitions
-Explainability
-Predictability
-More accurate than SOC, visualizes output (& modifiable), communicates uncertainty (eg grey-zone FFR-CT)
3⃣#AI & ML in #YesCCT #SCCT2021: New frontiers in atherosclerosis @AChoiHeart

-Use of #CNN for whole heart stenosis & atherosclerosis
-Improved reproducibility of stenosis to enhance guideline adherence
-Individualized risk prediction
-New Rx paradigm!
Read 7 tweets
What if you or your doctor could accurately predict how long you had to live upon a new diagnosis of aggressive cancer (e.g. lung cancer or sarcoma)? I've faced that question both as a doctor and with a dearly beloved. On the one hand I know I would 1/ #ML #AI #mortality
do the utmost to beat the odds forward.com/scribe/470514/… and a gloomy prediction would be just another hurdle to overcome. On the other hand, a very accurate predictor of mortality upon diagnosis would be very useful: we might dispense w control arms in trials [at our peril] 2/
families and society might allocate resources/support accordingly, research might focus on why exceptional patients deviate markedly from the prediction dbmi.hms.harvard.edu/news/most-powe… . Therefore a recent study by colleagues @HarvardDBMI @HarvardChanSPH @harvardmed on this prediction 3/
Read 8 tweets
What's wrong with Biostatistics is analogously related to the question that was put by the Queen to the Economists at the LSE after the GFC.
The Queen wondered why didn't the economists see it coming?
of course, health pandemics are different, but, the statistical models are not
Scholars working in the biomedical sciences, epidemiology, and #biostatistics spheres, rely on mathematical and applied statistical computing based on modelling assumptions that rely on historical data set observations.
The past cannot and will predict the future with certitude.
Even with Quantum Computing, Data Sciences, Machine Learning, Artificial Intelligence, or any other form of computer-aided Predictive Analytics, scholars across the domains of natural and social sciences will never be able to capture the emergence of rare #Black #Swan #Risks!
Read 13 tweets
I had attended a webinar recently and learnt something incredibly unique! I discovered that you could be a Data Scientist, but having a #specialisation is IMPORTANT!

What is a "specialisation"? How many kinds of specialisations are there in #DataScience Domain?

Thread🧵 Image
*Specialisation*
One can acquire all the skills of a Data Scientist, but having specialisation in a particular skill can set you apart from the rest. It can be anything! You can analyse data as no one else; data visualisation or database management (#DBMS) could be your niche.🤩
☑️Data Visualisation
If you have a knack for producing beautiful graphical representations from the data, this could be your domain of specialisation, and you could become a Data #Visualisation Engineer. Image
Read 10 tweets
Deep dive into "ZeRO: Memory Optimizations Toward Training Trillion Parameter Models" by Samyam Rajbhandari, Olatunji Ruwase, Yuxiong He & @jeffra45

It proposes an optimizer to build huge language pre-trained models.

Thread👇🏼 🔎
thesequence.substack.com/p/-edge22-mach…
Zero Redundancy Optimizer (ZeRO) is an optimization module that maximizes both memory and scaling efficiency.

2/
It tries to address the limitations of data parallelism and model parallelism while achieving the merits of both

thesequence.substack.com/p/-edge22-mach…

3/
Read 7 tweets
#COVID19India

Quite frankly, I don't (and couldn't know). I've mucked around from simple to ensemble #ML models over the last year, only to realize that something this complex cannot be modelled or predicted.

However, you can pick up what's happening, currently, based...
+
... off the standard epidemiological metrics - changes in trends, TPR, testing rates, recoveries etc. And what that means in terms of the near and medium-term horizons.

The most sensible benchmark would be TPR declining or levelling off against testing rates that are rising...
+
... against/ahead of case growth rates. If the data is passably reliable, it's a good indicator that a peak is to be expected, followed by a decline.

This would also show in R[t] hitting 1.0 on a decline and continuing to go under. If testing is doubtful, TPR is rising ...
+
Read 5 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!