A classical online course by Professor Gilbert Strang based on his popular textbook "Introduction to Linear Algebra". Learn about matrix theory and systems of equations.
https://t.co/GarhvVxXhG
Recently, I shared a list of some courses that were useful in my transition to machine learning.
While I took most of the courses in person, there are some alternative online courses you can check out.
Here is a thread of a few interesting online courses based on the list:
A classical online course by Professor Gilbert Strang based on his popular textbook "Introduction to Linear Algebra". Learn about matrix theory and systems of equations.
https://t.co/GarhvVxXhG
Learn about the geometry of complex numbers.
https://t.co/DgMuMCgAhr
Pay close attention to the chain rule as it's heavily referenced in machine learning, specifically when discussing optimization. This course is part of a specialization called MathTrackX. I recommend checking that as well.
https://t.co/H4hK05t44b
When you are working with machine learning algorithms applied to data you are dealing with information processing which in essence relies on ideas from information theory such as entropy. This course should provide the basics.
https://t.co/ETeMiwTry1
The courses in this specialization provide a great overview of data mining techniques used for structured and unstructured data.
https://t.co/oGzoOGOMnU
In machine learning, we are programming sophisticated algorithms and it's important to understand key concepts in this subject before jumping straight into ML algorithms. In general, an Algorithms course builds a strong CS foundation.
https://t.co/bdlXphoJud
Note: Includes courses for multivariate calculus and linear algebra. One of my favorite courses due to the quality of lectures and focused topics.
https://t.co/3Uf3iuni3z
This course is focused on the basics of statistics which is important when dealing with uncertainties, modeling, inference, etc. Although the courses focus on Python, there are other options using R as well.
https://t.co/yZOUQBTZNI
Probability can become a difficult topic but it's a core concept of building probabilistic prediction models. This course can provide an intuitive introduction to core topics like conditional probability.
https://t.co/sGirM58T9p
More from elvis
I have always emphasized on the importance of mathematics in machine learning.
Here is a compilation of resources (books, videos & papers) to get you going.
(Note: It's not an exhaustive list but I have carefully curated it based on my experience and observations)
📘 Mathematics for Machine Learning
by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong
https://t.co/zSpp67kJSg
Note: this is probably the place you want to start. Start slowly and work on some examples. Pay close attention to the notation and get comfortable with it.
📘 Pattern Recognition and Machine Learning
by Christopher Bishop
Note: Prior to the book above, this is the book that I used to recommend to get familiar with math-related concepts used in machine learning. A very solid book in my view and it's heavily referenced in academia.
📘 The Elements of Statistical Learning
by Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie
Mote: machine learning deals with data and in turn uncertainty which is what statistics teach. Get comfortable with topics like estimators, statistical significance,...
📘 Probability Theory: The Logic of Science
by E. T. Jaynes
Note: In machine learning, we are interested in building probabilistic models and thus you will come across concepts from probability theory like conditional probability and different probability distributions.
Here is a compilation of resources (books, videos & papers) to get you going.
(Note: It's not an exhaustive list but I have carefully curated it based on my experience and observations)
📘 Mathematics for Machine Learning
by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong
https://t.co/zSpp67kJSg
Note: this is probably the place you want to start. Start slowly and work on some examples. Pay close attention to the notation and get comfortable with it.
📘 Pattern Recognition and Machine Learning
by Christopher Bishop
Note: Prior to the book above, this is the book that I used to recommend to get familiar with math-related concepts used in machine learning. A very solid book in my view and it's heavily referenced in academia.
📘 The Elements of Statistical Learning
by Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie
Mote: machine learning deals with data and in turn uncertainty which is what statistics teach. Get comfortable with topics like estimators, statistical significance,...
📘 Probability Theory: The Logic of Science
by E. T. Jaynes
Note: In machine learning, we are interested in building probabilistic models and thus you will come across concepts from probability theory like conditional probability and different probability distributions.
The past month I've been writing detailed notes for the first 15 lectures of Stanford's NLP with Deep Learning. Notes contain code, equations, practical tips, references, etc.
As I tidy the notes, I need to figure out how to best publish them. Here are the topics covered so far:
I know there are a lot of you interested in these from what I gathered 1 month ago. I want to make sure they are high quality before publishing, so I will spend some time working on that. Stay
Below is the course I've been auditing. My advice is you take it slow, there are some advanced concepts in the lectures. It took me 1 month (~3 hrs a day) to take rough notes for the first 15 lectures. Note that this is one semester of
I'm super excited about this project because my plan is to make the content more accessible so that a beginner can consume it more easily. It's tiring but I will keep at it because I know many of you will enjoy and find them useful. More announcements coming soon!
NLP is evolving so fast, so one idea with these notes is to create a live document that could be easily maintained by the community. Something like what we did before with NLP Overview: https://t.co/Y8Z1Svjn24
Let me know if you have any thoughts on this?
As I tidy the notes, I need to figure out how to best publish them. Here are the topics covered so far:
I know there are a lot of you interested in these from what I gathered 1 month ago. I want to make sure they are high quality before publishing, so I will spend some time working on that. Stay
I've been writing notes for the latest Deep Learning for NLP course by Stanford.
— elvis (@omarsar0) January 14, 2022
For fun, I also started to add my own code snippets into the notes. I think this is a more efficient way to study: theory + code.
Plan to share these notes soon. Stay tuned! pic.twitter.com/hWzZDORbl6
Below is the course I've been auditing. My advice is you take it slow, there are some advanced concepts in the lectures. It took me 1 month (~3 hrs a day) to take rough notes for the first 15 lectures. Note that this is one semester of
I'm super excited about this project because my plan is to make the content more accessible so that a beginner can consume it more easily. It's tiring but I will keep at it because I know many of you will enjoy and find them useful. More announcements coming soon!
NLP is evolving so fast, so one idea with these notes is to create a live document that could be easily maintained by the community. Something like what we did before with NLP Overview: https://t.co/Y8Z1Svjn24
Let me know if you have any thoughts on this?
More from Education
Normally I enjoy the high standards of journalism in @guardian . Not today as disappointed with misleading headline that suggest infections are spreading fastest in children. It'll worry parents/teachers & I doubt most readers will unpick the
The latest REACT1 report shows prevalence of infection in ALL age groups has fallen, including children aged 5-12 from 1.59% in Round 8 to 0.86% in Round 9a. The authors of REACT1 report also (wisely) didn't try to interpret the prevalence figures.
If this were a research trial you wouldn't place much weight on the age differences in % prevalence because of the wide confidence intervals, i.e. differences weren't statistically significant.
3/
I've previously tweeted on the challenges (& dangers) of interpreting surveillance data. One would need lots more contextual info to make sense of it & arrive at sound
Undoubtedly some will extrapolate from the prevalence of infection figures in children to other settings i.e. schools based on the headline. I'd advise caution as there is a real risk of over-interpretation through extrapolation of limited data. Association is not causation.
5/
The latest REACT1 report shows prevalence of infection in ALL age groups has fallen, including children aged 5-12 from 1.59% in Round 8 to 0.86% in Round 9a. The authors of REACT1 report also (wisely) didn't try to interpret the prevalence figures.
If this were a research trial you wouldn't place much weight on the age differences in % prevalence because of the wide confidence intervals, i.e. differences weren't statistically significant.
3/
I've previously tweeted on the challenges (& dangers) of interpreting surveillance data. One would need lots more contextual info to make sense of it & arrive at sound
Misinterpretation of surveillance data is a serious issue. Surveillance data needs to come with a warning label - Open to biases - interpret with caution! Some may not realize that surveillance often does not measure all infection, it's a proxy for actual disease incidence.
— Andrew Lee (@andrewleedr) February 14, 2021
1/
Undoubtedly some will extrapolate from the prevalence of infection figures in children to other settings i.e. schools based on the headline. I'd advise caution as there is a real risk of over-interpretation through extrapolation of limited data. Association is not causation.
5/
Saturday Morning Graduate School Admissions/Funding Breakfast
• 1297 USA Scholarships
• 5 Hot Tips for current B.S, Master/PhD applicants
• Admission and FULL Funding Info to Sweden🇸🇪, Australia🇦🇺, France🇫🇷, Germany🇩🇪 and China🇹🇷
• 6 IGTV Videos
Follow @Okpala_IU
A Thread
Are you working hard to study full time (Bachelor, MS, MBA, PhD) in the United States of America🇺🇸?
Here are 1297 verified Scholarships for year 2021
Search here: https://t.co/3AHhW7RUfK
Follow @Okpala_IU for more
Watch other videos on IGTV:
5 Hot Tips for current Bachelor, Master/PhD applicants
1. Standardized Tests (TOEFL, GRE, GMAT)
Yes, the school may have waived it for admissions but providing it definitely increasing your chances of getting funded. If it strengthens your overall profile, that is excellent.
2. Do not trivialize Letters of Recommendations
Remember that your application packet (all supporting documents) is what is being looked at while you are being considered for admission and funding. A lot of schools read LoRs very carefully so ensure you get strong letters.
Read my notes on LoRs:
• 1297 USA Scholarships
• 5 Hot Tips for current B.S, Master/PhD applicants
• Admission and FULL Funding Info to Sweden🇸🇪, Australia🇦🇺, France🇫🇷, Germany🇩🇪 and China🇹🇷
• 6 IGTV Videos
Follow @Okpala_IU
A Thread
Are you working hard to study full time (Bachelor, MS, MBA, PhD) in the United States of America🇺🇸?
Here are 1297 verified Scholarships for year 2021
Search here: https://t.co/3AHhW7RUfK
Follow @Okpala_IU for more
Watch other videos on IGTV:
5 Hot Tips for current Bachelor, Master/PhD applicants
1. Standardized Tests (TOEFL, GRE, GMAT)
Yes, the school may have waived it for admissions but providing it definitely increasing your chances of getting funded. If it strengthens your overall profile, that is excellent.
2. Do not trivialize Letters of Recommendations
Remember that your application packet (all supporting documents) is what is being looked at while you are being considered for admission and funding. A lot of schools read LoRs very carefully so ensure you get strong letters.
Read my notes on LoRs:
If you are submitting a MS/PhD application for admission in the USA, this is for you.
— Ifeanyi Okpala (@Okpala_IU) June 23, 2020
Today, I am going to share one tip associated with the \u201cLetters of Recommendation\u201d required, which I think can make a lot of difference.
- Guiding your Recommenders on Information
Thread pic.twitter.com/uxPHB0W0Su
I get asked a lot how you can improve your skills and chances of getting a job as a developer. Best way is to work on a real-world project, deploy it, make it open-source, get feedback from others, share your knowledge, rinse, repeat.
Here are my top 7 project ideas. Thread 👇
1. 📊 Build an embeddable user feedback form (clone of https://t.co/xFHvT7iFEf) . Have a top notch design, fully working, minimal bugs, open-source, deploy it free on Heroku / Netlify / Vercel. If you can spare $11, buy a domain. Share with the whole world when done.
2. 🚀 Build a product roadmap SAAS.(https://t.co/Rq9DBeCMlh) Users can create new projects, create different stages for their projects. The community can submit project ideas, vote on existing ideas. Project owners pay a monthly fee per project.
3. ⛈️ Build a digital marketplace. (https://t.co/BWd1aeWMt5) Sellers can upload digital products for sale. Customers can purchase digital products and securely download. Sellers are paid out at the end of every month. Don't make it complicated, implement a great design.
4. 👨🏭 Build a job board software (https://t.co/EjWoMyqi9H). Companies can post jobs for a price, providing a link to the job application form. Jobs can be highlighted as urgent for an additional price.
Here are my top 7 project ideas. Thread 👇
1. 📊 Build an embeddable user feedback form (clone of https://t.co/xFHvT7iFEf) . Have a top notch design, fully working, minimal bugs, open-source, deploy it free on Heroku / Netlify / Vercel. If you can spare $11, buy a domain. Share with the whole world when done.
2. 🚀 Build a product roadmap SAAS.(https://t.co/Rq9DBeCMlh) Users can create new projects, create different stages for their projects. The community can submit project ideas, vote on existing ideas. Project owners pay a monthly fee per project.
3. ⛈️ Build a digital marketplace. (https://t.co/BWd1aeWMt5) Sellers can upload digital products for sale. Customers can purchase digital products and securely download. Sellers are paid out at the end of every month. Don't make it complicated, implement a great design.
4. 👨🏭 Build a job board software (https://t.co/EjWoMyqi9H). Companies can post jobs for a price, providing a link to the job application form. Jobs can be highlighted as urgent for an additional price.
You asked. So here are my thoughts on how osteopathic medical students should respond to the NBOME.
(thread)
Look, even before the Step 2 CS cancellation, my DMs and email were flooded with messages from osteopathic medical students who are fed up with the NBOME.
There is *real* anger toward this organization. Honestly, more than I even heard about from MD students and the NBME.
The question is, will that sentiment translate into action?
Amorphous anger on social media is easy to ignore. But if that anger gets channeled into organized efforts to facilitate change, then improvements are possible.
This much should be clear: begging the NBOME to reconsider their Level 2-PE exam is a waste of your time.
Best case scenario, you’ll get another “town hall” meeting, a handful of platitudes, and some thoughtful beard stroking before being told that they’re keeping the exam.
Instead of complaining to the NBOME, here are a few things that are more likely to bring about real change.
(thread)
I think most of us are over here waiting to see what @jbcarmody has to say about the latest NBOME email pic.twitter.com/bVWkS23V7z
— Jake Berg (@jberg521) January 28, 2021
Look, even before the Step 2 CS cancellation, my DMs and email were flooded with messages from osteopathic medical students who are fed up with the NBOME.
There is *real* anger toward this organization. Honestly, more than I even heard about from MD students and the NBME.
The question is, will that sentiment translate into action?
Amorphous anger on social media is easy to ignore. But if that anger gets channeled into organized efforts to facilitate change, then improvements are possible.
This much should be clear: begging the NBOME to reconsider their Level 2-PE exam is a waste of your time.
Best case scenario, you’ll get another “town hall” meeting, a handful of platitudes, and some thoughtful beard stroking before being told that they’re keeping the exam.
Instead of complaining to the NBOME, here are a few things that are more likely to bring about real change.
You May Also Like
https://t.co/6cRR2B3jBE
Viruses and other pathogens are often studied as stand-alone entities, despite that, in nature, they mostly live in multispecies associations called biofilms—both externally and within the host.
https://t.co/FBfXhUrH5d
Microorganisms in biofilms are enclosed by an extracellular matrix that confers protection and improves survival. Previous studies have shown that viruses can secondarily colonize preexisting biofilms, and viral biofilms have also been described.
...we raise the perspective that CoVs can persistently infect bats due to their association with biofilm structures. This phenomenon potentially provides an optimal environment for nonpathogenic & well-adapted viruses to interact with the host, as well as for viral recombination.
Biofilms can also enhance virion viability in extracellular environments, such as on fomites and in aquatic sediments, allowing viral persistence and dissemination.
Viruses and other pathogens are often studied as stand-alone entities, despite that, in nature, they mostly live in multispecies associations called biofilms—both externally and within the host.
https://t.co/FBfXhUrH5d
Microorganisms in biofilms are enclosed by an extracellular matrix that confers protection and improves survival. Previous studies have shown that viruses can secondarily colonize preexisting biofilms, and viral biofilms have also been described.
...we raise the perspective that CoVs can persistently infect bats due to their association with biofilm structures. This phenomenon potentially provides an optimal environment for nonpathogenic & well-adapted viruses to interact with the host, as well as for viral recombination.
Biofilms can also enhance virion viability in extracellular environments, such as on fomites and in aquatic sediments, allowing viral persistence and dissemination.
I think a plausible explanation is that whatever Corbyn says or does, his critics will denounce - no matter how much hypocrisy it necessitates.
Corbyn opposes the exploitation of foreign sweatshop-workers - Labour MPs complain he's like Nigel
He speaks up in defence of migrants - Labour MPs whinge that he's not listening to the public's very real concerns about immigration:
He's wrong to prioritise Labour Party members over the public:
He's wrong to prioritise the public over Labour Party
One of the oddest features of the Labour tax row is how raising allowances, which the media allowed the LDs to describe as progressive (in spite of evidence to contrary) through the coalition years, is now seen by everyone as very right wing
— Tom Clark (@prospect_clark) November 2, 2018
Corbyn opposes the exploitation of foreign sweatshop-workers - Labour MPs complain he's like Nigel
He speaks up in defence of migrants - Labour MPs whinge that he's not listening to the public's very real concerns about immigration:
He's wrong to prioritise Labour Party members over the public:
He's wrong to prioritise the public over Labour Party
