About Machine Learning
Machine learning is a method of data analysis that automates analytical model building. It is a branch
of Artificial Intelligence based on the idea that systems can learn from data, identify patterns and
make decisions with minimal human intervention. Because of new computing technologies, machine learning today is not like machine learning of the past. It was born from pattern recognition and the theory that computers can learn without being programmed to perform specific tasks; researchers interested in artificial intelligence wanted to see if computers could learn from data. The iterative aspect of machine learning is important because as models are exposed to new data, they are able to independently adapt. They learn from previous computations to produce reliable, repeatable decisions and results. It’s a science that’s not new but one that has gained fresh momentum.
“Machine learning, in the simplest terms, is the analysis of statistics to help computers make decisions base on repeatable characteristics found in the data.”
― Vardhan Kishore Agrawal.
About Advanced Machine Learning Specialization Program
This specialization gives an introduction to deep learning, reinforcement learning, natural language understanding, computer vision, and Bayesian methods. Top Kaggle machine learning practitioners and CERN scientists will share their experience of solving real-world problems and help you to fill the gaps between theory and practice. Upon completion of 7 courses, you will be able to apply modern machine learning methods in enterprise and understand the caveats of real-world data and settings.
What skill you will learn from this course?
In this course, you will gain expertise in topics such as:
- Recurrent, Neural Network, Tensor flow, and Convolutional Neural Network.
- Deep Learning and Data Analysis.
- Feature Extraction and Feature Engineering.
- Xgboost, Bayesian Optimization, and Gaussian Process.
- Markov Chain Monte Carlo (MCMC).
- Variational Bayesian Methods.
There are 7 Courses in this Specialization program:
1. Introduction to Deep Learning. (Content ratings 85%)
In this course, you will learn about the basic understanding of modern neural networks and their applications in computer vision and natural language understanding.
- Introduction to optimization- In the first module you will learn about linear models and stochastic optimization methods.
- Introduction to neural networks- This module is an introduction to the concept of a deep neural network.
- Deep Learning for images- In this module you will learn about building blocks of deep learning for image input.
- Unsupervised representation learning- In this module you are going to dive into unsupervised parts of deep learning.
- Deep learning for sequences- In this module, you will learn how to use deep learning for sequences such as texts, video, audio, etc.
- Final Project- In this module, you will apply all your knowledge about neural networks for images and texts for the final project.
2. How to win a Data Science Competition: Learn from Top Kagglers. (94%)
If you want to break into competitive data science, then this course is for you! Participating in predictive modeling competitions can help you gain practical experience, improve, and harness your data modeling skills.
- Introduction & Recap- This chapter will introduce competitive data science. You will learn about the competitions’ mechanics.
- Feature Preprocessing and Generation with Respect to Models- This module will summarize approaches to work with features: preprocessing, generation and extraction
- Final Project Description- In this course, you will start on the final project, in fact, a competition, in this module, you can find an information about it.
- Exploratory Data Analysis- Will start with Exploratory Data Analysis (EDA). It is a very broad and exciting topic and an essential component of solving the process.
- Validation- This module will discuss various validation strategies. you will see that the strategy you choose depends on the competition setup.
- Data Leakages- This module will cover something very unique to data science competitions.
- Metrics Optimization- This chapter will first focus on another component of the competitions: the evaluation metrics.
- Advanced Feature Engineering – In this chapter, you will study a very powerful technique for feature generation.
- Hyperparameter Optimization – This module talks about the hyperparameter optimization process. You will also have a special video with practical tips and tricks, recorded by four instructors.
- Advanced feature engineering II- In this chapter, you will learn about a few more advanced feature engineering techniques.
- Ensembling- Nowadays it is hard to find a competition won by a single model! Every winning solution incorporates ensembles of models.
- Competitions go through- For the 5th chapter you have prepared for you several “walk-through” videos.
- Final Project- Final project for the course.
3. Bayesian Methods for Machine Learning. (84%)
People apply Bayesian methods in many areas: from game development to drug discovery. They give superpowers to many machine learning algorithms.
- Introduction to Bayesian methods & Conjugate priors- In this module, you will discuss what bayesian methods are and what are probabilistic models.
- Expectation-Maximization algorithm- You will learn about the central topic in probabilistic modeling: the Latent Variable Models and how to train them, namely the Expectation-Maximization algorithm.
- Variational Inference & Latent Dirichlet Allocation- This time you will move on to approximate inference methods.
- Markov chain Monte Carlo- You will learn how to approximate training and inference with sampling and how to sample from complicated distributions.
- Variational Autoencoder- In this module, you will combine many ideas from the previous weeks and add some new to build Variational Autoencoder a model that can learn a distribution over structured data.
- Gaussian processes & Bayesian optimization- This time you will see nonparametric Bayesian methods.
- Final project- In this module, you will apply methods that you learned in this course to this final project.
4. Practical Reinforcement Learning. (81%)
Here you will find out about the foundations of RL methods: value/policy iteration, q-learning, policy gradient, etc.
- Intro: why should you care- In this chapter you are going to define and taste what reinforcement learning is about.
- At the heart of RL: Dynamic Programming- You will consider the reinforcement learning formalisms in a more rigorous, mathematical way.
- Model-free methods- In this chapter, you will find out how to apply last week’s ideas to real-world problems: ones where you don’t have a perfect model of your environment.
- Approximate Value Based Methods- You will learn to scale things even farther up by training agents based on neural networks.
- Policy-based methods- You spent 3 previous modules working on the value-based methods: learning state values, action values, and whatnot.
- Exploration- In this final chapter you will learn how to build better exploration strategies with a focus on contextual bandit setup.
5. Deep Learning in Computer vision. (83%)
Deep learning added a huge boost to the already rapidly developing field of computer vision.
- Introduction to image processing and computer vision- In the first introductory module you will learn about the purpose of computer vision, digital images, and operations that can be applied to them, like brightness and contrast correction, convolution, and linear filtering.
- Convolutional features for visual recognition- Module two revolves around general principles underlying modern computer vision architectures based on deep convolutional neural networks.
- Object detection- In this third module you focus on the object detection task — one of the central problems in vision.
- Object tracking and action recognition- The fourth module of our course focuses on video analysis and includes material on optical flow estimation, visual object tracking, and action recognition.
- Image segmentation and synthesis- In the last module of this course, You should consider problems where the goal is to predict the entire image.
6. Natural Language Processing. (88%)
This course covers a wide range of tasks in Natural Language Processing from basic to advanced: sentiment analysis, summarization, dialogue state tracking, to name a few.
- Intro and text classification- In this module, you will have two parts: first, a broad overview of NLP area and your course goals, and second, a text classification task.
- Language modeling and sequence tagging- In this module, you will treat texts as sequences of words. You will learn how to predict the next words given some previous words.
- Vector Space Models of Semantics- In this chapter, you will learn vectors that represent meanings. First, you will discuss traditional models of distributional semantics.
- Sequence to sequence tasks- Nearly any task in NLP can be formulated as a sequence to sequence tasks: machine translation, summarization, question answering, and many more.
- Dialog systems- In this module you will overview so-called task-oriented dialog systems like Apple Siri or Amazon Alexa.
7. Addressing Large Hadron Collider Challenges by Machine Learning. (90%)
The Large Hadron Collider (LHC) is the largest data generation machine for the time being. It doesn’t produce the big data, the data is gigantic.
- Introduction into particle physics for data scientists- This module starts with a mild introduction into particle physics, and it explains basic notions.
- Particle identification- This module is about detectors in high energy physics. It describes several detector designs, different detector systems.
- Search for New Physics in Rare Decays- In this module, You explain how a new physics search can be mediated through a search for rare processes.
- Search for Dark Matter Hints with Machine Learning at a new CERN experiment- This module learns to you start this module with an explanation of what the Dark Matter phenomenon is about and what are the general strategies for the Dark Matter search.
- Detector optimization- This module covers several cases of detector design optimization in high energy physics experiments using Bayesian optimization with Gaussian processes.
Note: Your review matters
If you have already done this course, kindly drop your review in our reviews section. It would help others to get useful information and better insight into the course offered.
- About our policies and review criteria.
- How can you choose and compare online courses?
- How to add Courses to your Wishlist?
- You can suggest courses to add to our website.
- In terms of quality of the material this course will absolutely meet your requirements.
- One with graduate level math skills can also commence with this course.
- Assignments are good for getting to know python tools.
- Need to improve the quality of content in Bayesian methods for machine learning course.
- Require quite a bit of probability theory knowledge.
- The teachers should put more time into explaining the models and their details.
Specification: Advanced Machine Learning Specialization