Giter VIP home page Giter VIP logo

coursera-learning's Introduction

coursera-learning

This is a repo for storing my labworks on Coursera, all secured with passwords.

Coursera has an honor code, requesting that you should never make any content of your homework publicly available. So I've locked them up in archives.

It's just for backup, not sharing.

For those who might be interested in starting their own journey in MOOC platforms like Coursera, I have written a memo/guide here.

Coursera Learning Notes by Zhu Li on 2018.4.6.

All archives in this repo are locked, please don't bother cracking, there's nothing valuable inside after all, just a pile of my old homework.

If you think you've found something useful here, feel free to leave a star. I'll be glad to know if my action is making this world better, by raising a helping hand.

Finished Courses

Algorithms Part I

  • Organization: Princeton University
  • URL: Algorithms, Part I | Coursera
  • Time: April 2, 2017
  • Grade: 98.6/100
  • Topic: data structure, algorithm, Java
  • Review: The lecture speed was a bit too slow, so I had to go at between 1.25x and 1.5x speed to save time. Everything is really well explained, making this course very friendly even for fresh beginners. Actually I signed up for this just to do a little practice in Java programming. Considering the ammount of work devoted to the programming assignments, it was a wise decision to join up, well worth the time and efforts.

Machine Learning

  • Organization: Stanford University
  • URL: Machine Learning | Coursera
  • Time: April 29, 2017
  • Grade: 100/100
  • Topic: machine learning, Matlab
  • Review: This is one of the "founding courses" of Coursera, thus it is supposed to be easy and interesting (otherwise people would've been scared off in the first place). So it is vital, for every programming assignment, that you try to read and understand the 99% of codes already written for you. The 1% for you to finish is really the trivial part. Otherwise there'll be no gain at all. Also it's fresh experience for those who get to think in a vectorized manner for the first time.

Functional Programming Principles in Scala

  • Organization: École Polytechnique Fédérale de Lausanne
  • URL: Functional Programming Principles in Scala | Coursera
  • Time: May 10, 2017
  • Grade: 100/100
  • Topic: functional programming, Scala
  • Review: A course to learn Scala as well as functional programming. I'm a freshman for FP, so the programming assignments did give me a little challenge. I guess when one gots so fixed in the mindsets of imperative and objective programming, the adaptation to FP can be rough. I'm gonna finish the whole specialization, as they're all free for now : )

Functional Program Design in Scala

Discrete Optimization

  • Organization: University of Melbourne
  • URL: Discrete Optimization | Coursera
  • Time: July 5, 2017
  • Grade: 93/100
  • Topic: combinatorial optimization, meta-heuristics, randomization
  • Review: Very challenging course which requires solid programming skill and lots of paper reading. Given the hands-on experience related to optimization techniques, it's totally worth all the time and efforts.

Parallel Programming

Game Theory

Big Data Analysis with Scala and Spark

  • Organization: École Polytechnique Fédérale de Lausanne
  • URL: Big Data Analysis with Scala and Spark | Coursera
  • Time: August 12, 2017
  • Grade: 100/100
  • Topic: scala programming, parallel computing, spark programming
  • Review: Fourth course of the specialization, relatively short and easy. The programming assignments took me a whole lot of time putting the APIs right. It's something you have to go through when learning a computation framework, no way around. Besides, the lecturer talks rather fast, with 1.5x play speed and no caption, I had the opportunity to practice my listening skill, that's the real fun.

Introduction to Data Science in Python

  • Organization: University of Michigan
  • URL: Introduction to Data Science in Python | Coursera
  • Time: August 30, 2017
  • Grade: 100/100
  • Topic: python programming, pandas, data science
  • Review: An introductory course in ipython and pandas. The interactive notebook called "Jupyter" has nice user experience. If you're looking to learn some pandas programming, try it out.

Functional Programming in Scala Capstone

  • Organization: École Polytechnique Fédérale de Lausanne
  • URL: Functional Programming in Scala Capstone | Coursera
  • Time: September 3, 2017
  • Grade: 100/100
  • Topic: scala programming, parallel computing, data visualization, spark programming
  • Review: Fifth course of the specialization, a step-by-step guide to a full scale project. The programming is challenging, while not at maths and algorithm, but at parallel programming, memorization, functional programming, all sorts of tweaking to make your code faster and tighter. The grader has a pretty tight memory limit of 1.5GB, which turned out to be a real headache, for you can experience failures randomly, making the programming assignment unnecessarily much harder. Still, every bit of effort pays off. Try it and see for yourself.

Microeconomics Principles

Model Thinking

  • Organization: University of Michigan
  • URL: Model Thinking | Coursera
  • Time: October 13, 2017
  • Grade: 100/100
  • Topic: social science
  • Review: An introductory course in social sciences. It's totally for high school students and undergraduate freshmen, with no rigorous math or hands-on case study projects. I guess I'm too old for this.

Introduction to Programming with MATLAB

Applied Machine Learning in Python

  • Organization: University of Michigan
  • URL: Applied Machine Learning in Python | Coursera
  • Time: October 23, 2017
  • Grade: 100/100
  • Topic: machine learning, scikit-learn, pandas, numpy
  • Review: A very well-designed course, teach you to do machine learning by calling all sorts of APIs. Actually, for small to middle-sized datasets, I think this kind of approach is quite handy, or shall we say, "lightweight". For extremely large datasets, small samples can be analyzed with toolkits like this to help make some sense, before we embark on deep learning and system-level optimizations.

Applied Text Mining in Python

Bayesian Statistics: From Concept to Data Analysis

Algorithms Part II

  • Organization: Princeton University
  • URL: Algorithms, Part II | Coursera
  • Time: December 30, 2017
  • Grade: 100/100
  • Topic: data structure, algorithm, Java
  • Review: After being gone for so long, this course is finally back. I don't really expect to learn anything new from it, just for old times' sake. The quizzes are gone, replaced by optional interview problems. The programming assignments are also much easier. If you're new to Computer Science, this is one of the courses you can't miss.

Probabilistic Graphical Models 1: Representation

  • Organization: Stanford University
  • URL: Probabilistic Graphical Models 1: Representation | Coursera
  • Time: January 4, 2018
  • Grade: 100/100
  • Topic: bayesian inference, markov model, matlab
  • Review: This is the first course of the PGM series, which teaches you some basics of Bayesian inference, Markov network, factor graphs, etc. It's gonna be the building blocks of the bigger picture. If you're not quite familiar with algebra, calculus and probability theory, you're gonna have a hard time doing this. Also, this course is created in 2012, when Python han't risen to power, so you'll have to make do with Matlab. The programming assignments are about 50% reading comprehension, 40% researching and 10% coding. Make sure you take the time to do it by yourself. Cheating only takes ten minutes, and you'll gain nothing from it.

Neural Networks and Deep Learning

  • Organization: deeplearning.ai
  • URL: Neural Networks and Deep Learning | Coursera
  • Time: January 7, 2018
  • Grade: 100/100
  • Topic: deep learning, neural network, python
  • Review: This is the first course of the deep learning specialization by Professor Andrew Ng. It's explicitly made extremely easy because they wish to let AI and Deep learning be known to the general public, not just math/CS/stats professionals. The course is a brief introduction on basic feedforward neural network. If you're a CS major, you're supposed to be able to finish this course within 3 days. Still, the interviews with several leading figures is the greatest part of this course. It is the "sense" from those academic masters that's the most valuable part, which we should try to perceive and follow. The programming assignments are organized as step-by-step tutorials, which take on average within 2 hours to finish.

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

Structuring Machine Learning Projects

  • Organization: deeplearning.ai
  • URL: Structuring Machine Learning Projects | Coursera
  • Time: January 12, 2018
  • Grade: 100/100
  • Topic: deep learning, alchemy
  • Review: This is the third course of the deep learning specialization by Professor Andrew Ng. It's a two-week lecture on the techniques, rules and inspirations on the strategies to appply when working on deep learning projects. It's basically about rules of thumbs, so don't try to obey everything to the letter and expect things to work like wonder if you do. Think about it, learn from it, reflect upon it. Still, the most valuable part is always the interview with key figures from academia and industry.

Convolutional Neural Networks

  • Organization: deeplearning.ai
  • URL: Convolutional Neural Networks | Coursera
  • Time: January 21, 2018
  • Grade: 100/100
  • Topic: deep learning, alchemy
  • Review: This is the fourth course of the deep learning specialization by Professor Andrew Ng. It's about one of hottest catchphrases, CNN. Convolutional neural network is indeed powerful, in that it's much more effecient and flexible than old-school MLP. Things also begin to get really misty from this point, as you see one magical model after another, without getting any sense where the hell is the explainability. If there's anything that's actually illuminating, it's the feature visualization of CNN and neural style transfer that help you make sense of what every part of a huge CNN can possibly do and what the hidden layers mean.

Python Data Visualization

Sequence Models

  • Organization: deeplearning.ai
  • URL: Sequence Models | Coursera
  • Time: February 23, 2018
  • Grade: 100/100
  • Topic: deep learning, natural language processing, black magic
  • Review: This is the last course of the deep learning specialization by Professor Andrew Ng. It's said this one has been postponed for twice already, even this session was three days late for its declared launch date. I can possibly imagine what kind of tight schedule they've been working on to put things together. The course itself is good, but too sloppy. The learning experience is not quite enjoyable for a paid course. I expected better.

Bitcoin and Cryptocurrency Technologies

  • Organization: Princeton University
  • URL: Bitcoin and Cryptocurrency Technologies | Coursera
  • Time: March 24, 2018
  • Grade: 92.3/100
  • Topic: bitcoin, blockchain, distributed computing
  • Review: I'm glad Princeton presented a course for cryptocurrency for tech professionals. I'd really love to learn some stuff that have great potential for a long-lasting impact in industry, not a tulip bubble or some foolish zero-sum games. That's why I choose to view blockchain and cryptocurrency as two separate ideas, of which the former is of more value to me.

Financial Accounting: Foundations

  • Organization: University of Illinois Urbana-Champaign
  • URL: Financial Accounting: Foundations | Coursera
  • Time: April 7, 2018
  • Grade: 100/100
  • Topic: finance, accounting
  • Review: This is the first course of the Financial Management Specialization, I take this course to learn something about accounting, as a prior knowledge to financial engineering. The peer-reviewed assignment is good, though not enough people are willing to pay to join up, so you don't have as many classmates around the world to share insights with. Still, peer review is a very idea-inspiring process, it's quite different from working on computer programms and expect things to work exactly as you command. You actually seek difference from your own. Investopedia is a good place to drop by. You never get disappointed.

Financial Accounting: Advanced Topics

  • Organization: University of Illinois Urbana-Champaign
  • URL: Financial Accounting: Advanced Topics | Coursera
  • Time: April 9, 2018
  • Grade: 99/100
  • Topic: finance, accounting
  • Review: This is the second course of the Financial Management Specialization, still a short four-module course, with 4 quizzes and 1 peer-reviewed assignment. The number of participants seemed a bit low, I had no choice but to wait a whole day before getting any response and having my assignment graded. Still, I'm much luckier than the fellows I helped review. They actually waited a week or a month, you believe that? My god. I'm glad I helped them out.

Investments I: Fundamentals of Performance Evaluation

  • Organization: University of Illinois Urbana-Champaign
  • URL: Financial Investments I: Fundamentals of Performance Evaluation | Coursera
  • Time: April 29, 2018
  • Grade: 97.1/100
  • Topic: finance, accounting, investment
  • Review: This is the third course of the Financial Management Specialization, a four-module course. Brace yourself because this is a rather intensive one, with extremely long lectures and several peer-reviewed assignments. Don't rush to finish it by skipping the videos and go directly for the homework. I find watching the lectures very rewarding because Professor Weisbenner is a rather funny guy and his lectures share a lot of insights and experiences, which is far more valuable than what you'll get by simply finishing the course. Take the chance to communicate with brilliant minds whenever you have the chance. Homeworks are trivial if you've really devoted yourself to the learnig process and tried to enjoy it, otherwise they'll just be chores and boring to the death. I have a memo for this course on Zhihu.

Investments II: Lessons and Applications for Investors

Private Equity and Venture Capital

  • Organization: Università Bocconi
  • URL: Private Equity and Venture Capital | Coursera
  • Time: May 12, 2018
  • Grade: 100/100
  • Topic: private equity, venture capital, finance
  • Review: This is an introductory course on private equity and venture capital, without explicit need for background knowledge in finance, economics and accounting. It would be good to learn something like this before you embark on some serious education in finance and investment. It's a good starting point, well worth the time.

Corporate Finance I: Measuring and Promoting Value Creation

Corporate Finance II: Financing Investments and Managing Risk

Moralities of Everyday Life

  • Organization: Yale University
  • URL: Moralities of Everyday Life | Coursera
  • Time: September 15, 2018
  • Grade: 100/100
  • Topic: psychology, philosophy, sociology
  • Review: This isn't a course that teaches you anything practical in terms of job-seeking or money-making. It's about more profound questions of human society and existence. If elite universities like Harvard and Yale are deemed as elites, this is the type of education that makes them qualified.

The Global Financial Crisis

  • Organization: Yale University
  • URL: The Global Financial Crisis | Coursera
  • Time: September 27, 2018
  • Grade: 100/100
  • Topic: economics, finance
  • Review: This is an in-depth case study course for the global financial crisis. It's accompanied by sufficient quizzes and lectured by Yale professor Andrew Metrick and former Secretary of Treasury Timothy Geithner. Yale quality, don't miss it.

Financial Markets

  • Organization: Yale University
  • URL: Financial Markets | Coursera
  • Time: October 14, 2018
  • Grade: 100/100
  • Topic: economics, finance
  • Review: This is an introductory course in finance. I just want to hear some advice from a Nobel Prize laureate.

Firm Level Economics: Consumer and Producer Behavior

Practical Time Series Analysis

  • Organization: State University of New York
  • URL: Practical Time Series Analysis | Coursera
  • Time: February 15, 2019
  • Grade: 100/100
  • Topic: time series analysis, stochastic process
  • Review: I thought this course was easy, but it turned out to be more mathy than I expected. The things taught here are rather traditional, but can be good training for a data scientist. Neural networks are expressive, but not so intepretable. Better learn some maths to keep your brain from getting so rusty, that you can only rely on superstition of RNG and SGD.It's the way of thinking that's worth the time and efforts. I have a memo here.

Firm Level Economics: Markets and Allocations

What is Data Science?

Open Source tools for Data Science

Data Science Methodology

Python for Data Science

Databases and SQL for Data Science

  • Organization: IBM
  • URL: Databases and SQL for Data Science | Coursera
  • Time: March 22, 2019
  • Grade: 100/100
  • Topic: python, sql
  • Review: It's easy, but no longer a no-brainer course. At least it takes you some time to design the sql query. One thing especially terrible about this course is the DB2 Console, just lame. The resource quota allocated for you was just too thin to make it work normally. Apart from this, I would say this course is still well-organized, if only we could do it with MySQL and Jupyter Notebook. It's IBM course after all, what else can I say? I expect better QoS from you, IBM.

Data Analysis with Python

Data Visualization with Python

Machine Learning with Python

  • Organization: IBM
  • URL: Machine Learning with Python | Coursera
  • Time: April 6, 2019
  • Grade: 100/100
  • Topic: python, pandas, scikit-learn
  • Review: This is actually the capstone course for another specialization. Well-organized and user-friendly, I would say. It's basically an sklearn tutorial.

Introduction to Mathematical Thinking

  • Organization: Stanford University
  • URL: Introduction to Mathematical Thinking | Coursera
  • Time: April 26, 2019
  • Grade: 100/100
  • Topic: mathematics
  • Review: This is a rather interesting math course. It's very inspiring and not too tough. Try it if you're still undergraduate-level. If you're already getting a Master or Doctor's degree, it's gonna be too easy for you, thus spoiling the fun.

Getting Started with Go

Functions, Methods, and Interfaces in Go

Concurrency in Go

Introduction to User Experience Design

Mathematics for Machine Learning: Linear Algebra

Mathematics for Machine Learning: Multivariate Calculus

Mathematics for Machine Learning: PCA

Microservices - Fundamentals

Developing and Deploying Microservices with Microclimate

  • Organization: IBM
  • URL: Developing and Deploying Microservices with Microclimate | Coursera
  • Time: September 11, 2019
  • Grade: 99/100
  • Topic: devops, microservice
  • Review: This is the second course of the IBM Microservices Specialization. I'm even less impressed with this one. Some course contents are directly copied from course 1. Is that responsible for students who paid? Besides, it's not difficult to see that the Microclimate product is out of maintenance, as their CICD pipeline docker image doesn't even build. IBM was a great company. Their ideas still are, but their blades already rusty.

Introduction to Augmented Reality and ARCore

IBM Cloud: Deploying Microservices with Kubernetes

IBM Cloud Private: Deploying Microservices with Kubernetes

Introduction to HTML5

Introduction to CSS3

Interactivity with JavaScript

Advanced Styling with Responsive Design

Divide and Conquer, Sorting and Searching, and Randomized Algorithms

Programming for Everybody (Getting Started with Python)

Python Data Structures

Using Python to Access Web Data

Using Databases with Python

Capstone: Retrieving, Processing, and Visualizing Data with Python

Java Programming: Solving Problems with Software

Java Programming: Arrays, Lists, and Structured Data

coursera-learning's People

Contributors

zhuli19901106 avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.