Coursera – Advanced Machine Learning Specialization (7 Courses) 2020-6

Description

The advanced machine learning specialization courses on the Coursera website are designed to teach you the latest techniques, artificial intelligence, familiar works and computer programming to solve the problems of industrial implementation of the game. See, read and speak to explain it. . This set consists of 7 courses that cover the topics of artificial intelligence as comprehensively and in detail as possible.

In the first course in this series you will learn in depth and work with neural networks, modern meetings. In a second course, you will learn how to run a data science competition and learn advanced topics in the field. In the third period, Bayesian machine learning methods are familiar. The fourth volume, which relates to reinforcement learning, can be and the fifth part of the topic Deep Learning in Vision, Computer Explained. In the sixth course, you need to deal with natural language processing, and in the seventh part, you can deploy the LHC’s machine learning solution.

Cases in which the course is taught:

Deep learning and working with neural networks
Data science
Bayesian methods for machine learning
Reinforcement learning
Deep Learning in Vision, Computers
Natural Language Processing
Solve the challenges of the LHC with machine learning

Profile the Advanced Machine Learning Specialization course:

Language: English
Duration: 214 hours
Number of courses: –
Education level: intermediate
Lecturer: Evgeny Sokolo
File format: mp4

This course

Introduction to optimization

Introduction to neural networks

Deep learning for images

We can use unsupervised representation learning

Deep learning for sequences

Introduction and summary

Feature preprocessing and generation related to models

Final project description

Exploratory data analysis

Metric optimization

Hyperparameter optimization

Competitions are taking place

Introduction to Bayesian inference methods and conjugate priors

Expectation maximization algorithm

Variational inference and latent Dirichlet assignment

Markov chain Monte Carlo

Variational autoencoder

Gaussian processes and Bayesian inference optimization

Introduction: Why should I care?

The heart of RL: dynamic programming

Model-free methods

Proximity-based methods

Policy-based methods

Exploration

Introduction to image processing and computer vision

Convolution functions for visual recognition

Object detection

Object tracking and action recognition

Image segmentation and synthesis

Introduction and text classification

Language modeling and sequence tagging

Vector space models of semantics

Order for tasks

Dialogue systems

Introduction to particle physics for data scientists

Particle identification

Search for new physics in rare decays

Use machine learning to search for clues about dark matter at the new CERN experiment

Detector optimization

Prerequisite course

As prerequisites we set analysis and linear algebra (especially derivatives, matrices and operations with them), probability theory (random variables, distributions, moments), basic programming in Python (functions, loops, Numpy), basic machine learning (linear models, decision trees, boosting and Random Forests). Our target audience is anyone who is already familiar with the basics of machine learning and would like to gain practical experience in research and development in the field of modern machine learning.