Picture by Writer
For these diving into the world of laptop science or needing a touch-up on their likelihood data, you’re in for a deal with. Stanford College has lately up to date its YouTube playlist on its CS109 course with new content material!
The playlist contains 29 lectures to offer you gold-standard data of the fundamentals of likelihood principle, important ideas in likelihood principle, mathematical instruments for analyzing chances, after which ending information evaluation and Machine Studying.
So let’s get straight into it…
Hyperlink: Counting
Study in regards to the historical past of likelihood and the way it has helped us obtain trendy AI, with real-life examples of growing AI programs. Perceive the core counting phases, counting with ‘steps’ and counting with ‘or’. This consists of areas comparable to synthetic neural networks and the way researchers would use likelihood to construct machines.
Hyperlink: Combinatorics
The second lecture goes into the following degree of seriousness counting – that is referred to as Combinatorics. Combinatorics is the arithmetic of counting and arranging. Dive into counting duties on n objects, by way of sorting objects (permutations), selecting okay objects (combos), and placing objects in r buckets.
Hyperlink: What’s Likelihood?
That is the place the course actually begins to dive into Likelihood. Study in regards to the core guidelines of likelihood with a variety of examples and a contact on the Python programming language and its use with likelihood.
Hyperlink: Likelihood and Bayes
On this lecture, you’ll dive into studying methods to use conditional chances, chain rule, the regulation of complete likelihood and Bayes theorem.
Hyperlink: Independence
On this lecture, you’ll find out about likelihood in respect of it being mutually unique and unbiased, utilizing AND/OR. The lecture will undergo a wide range of examples so that you can get a great grasp.
Hyperlink: Random Variables and Expectations
Primarily based on the earlier lectures and your data of conditional chances and independence, this lecture will dive into random variables, use and produce the likelihood mass perform of a random variable, and have the ability to calculate expectations.
Hyperlink: Variance Bernoulli Binomial
You’ll now use your data to resolve tougher and tougher issues. Your objective for this lecture might be to recognise and use Binomial Random Variables, Bernoulli Random Variables, and have the ability to calculate the variance for random variables.
Hyperlink: Poisson
Poisson is nice when you could have a price and also you care in regards to the variety of occurrences. You’ll find out about how it may be utilized in completely different elements together with Python code examples.
Hyperlink: Steady Random Variables
The targets of this lecture will embrace being snug utilizing new discrete random variables, integrating a density perform to get a likelihood, and utilizing a cumulative perform to get a likelihood.
Hyperlink: Regular Distribution
You could have heard this about regular distribution earlier than, on this lecture, you’ll undergo a quick historical past of regular distribution, what it’s, why it can be crucial and sensible examples.
Hyperlink: Joint Distributions
Within the earlier lectures, you should have labored with 2 random variables at most, the following step of studying might be to enter any given variety of random variables.
Hyperlink: Inference
The educational objective of this lecture is methods to use multinomials, recognize the utility of log chances, and have the ability to use the Bayes theorem with random variables.
Hyperlink: Inference II
The educational objective continues from the final lecture of mixing Bayes theorem with random variables.
Hyperlink: Modelling
On this lecture, you’ll take the whole lot you could have realized to date and put it into perspective about real-life issues – probabilistic modelling. That is taking a complete bunch of random variables being random collectively.
Hyperlink: Normal Inference
You’ll dive into normal inference, and specifically, find out about an algorithm referred to as rejection sampling.
Hyperlink: Beta
This lecture will go into the random variables of chances that are used to resolve real-world issues. Beta is a distribution for chances, the place its vary values between 0 and 1.
Hyperlink: Including Random Variables I
At this level of the course, you’ll be studying about deep principle and including random variables is an introduction to methods to attain outcomes of the idea of likelihood.
Hyperlink: Central Restrict Theorem
On this lecture, you’ll dive into the central restrict theorem which is a crucial component in likelihood. You’ll undergo sensible examples so that you could grasp the idea.
Hyperlink: Bootstrapping and P-Values I
You’ll now transfer into uncertainty principle, sampling and bootstrapping which is impressed by the central restrict theorem. You’ll undergo sensible examples.
Hyperlink: Algorithmic Evaluation
On this lecture, you’ll dive a bit extra into laptop science with an in-depth understanding of the evaluation of algorithms, which is the method of discovering the computational complexity of algorithms.
Hyperlink: M.L.E.
This lecture will dive into parameter estimation, which is able to offer you extra data on machine studying. That is the place you are taking your data of likelihood and apply it to machine studying and synthetic intelligence.
Hyperlink: M.A.P.
We’re nonetheless on the stage of taking core rules of likelihood and the way it utilized to machine studying. On this lecture, you’ll deal with parameters in machine studying concerning likelihood and random variables.
Hyperlink: Naive Bayes
Naive Bayes is the primary machine studying algorithm you’ll find out about in depth. You’ll have learnt in regards to the principle of parameter estimation, and now will transfer on to how core algorithms comparable to Naive Bayes result in concepts comparable to neural networks.
Hyperlink: Logistic Regression
On this lecture, you’ll dive right into a second algorithm referred to as Logistic regression which is used for classification duties, which additionally, you will study extra about.
Hyperlink: Deep Studying
As you’ve began to dive into machine studying, this lecture will go into additional element about deep studying based mostly on what you could have already realized.
Hyperlink: Equity
We reside in a world the place machine studying is being carried out in our day-to-day lives. On this lecture, you’ll look into the equity round machine studying, with a deal with ethics.
Hyperlink: Superior Likelihood
You might have learnt lots in regards to the fundamentals of likelihood and have utilized it in numerous situations and the way it pertains to machine studying algorithms. The following step is to get a bit extra superior about likelihood.
Hyperlink: Way forward for Likelihood
The educational objective for this lecture is to find out about using likelihood and the number of issues that likelihood might be utilized to resolve these issues.
Hyperlink: Last Evaluate
And final however not least, the final lecture. You’ll undergo all the opposite 28 lectures and contact on any uncertainties.
With the ability to discover good materials to your studying journey might be tough. This likelihood for laptop science course materials is superb and can assist you grasp ideas of likelihood that you simply have been uncertain of or wanted a contact up.
Nisha Arya is a Knowledge Scientist and Freelance Technical Author. She is especially considering offering Knowledge Science profession recommendation or tutorials and principle based mostly data round Knowledge Science. She additionally needs to discover the alternative ways Synthetic Intelligence is/can profit the longevity of human life. A eager learner, in search of to broaden her tech data and writing expertise, while serving to information others.