AI: Learn Deep Learning with DL4J | IT Training & Certification | Info Trek
Respect Your Dreams
Follow through on your goals with courses

AI: Learn Deep Learning with DL4J

  • Private Class Icon
    Private Class
    • All of our private classes are customized to your organization's needs.

      Click on the button below to send us your details and you will be contacted shortly.
    3 Days

Course Details

Expand All
In this course, students will learn about the fundamentals of deep learning. The basic knowledges and building blocks to build neural networks will be learned steps by steps. Common use cases with the input data types will be elaborated. The focus is to get students able to perform hands-on codes practice and leverage to other practical use cases.
In this course, students will learn about the fundamentals of deep learning. The basic knowledges and building blocks to build neural networks will be learned steps by steps. Common use cases with the input data types will be elaborated. The focus is to get students able to perform hands-on codes practice and leverage to other practical use cases.

Before attending this course, students must have:

An understanding of Java language or some familiarity with other object oriented languages such as C++ and Python. Background in linear regression, basic statistics and/or machine learning will be helpful in understanding the mathematics background of neural networks. Proficient in one of the operating system- linux, Windows, MacOS, or centOS.

Before attending this course, students must have:

An understanding of Java language or some familiarity with other object oriented languages such as C++ and Python. Background in linear regression, basic statistics and/or machine learning will be helpful in understanding the mathematics background of neural networks. Proficient in one of the operating system- linux, Windows, MacOS, or centOS.

After completing this course, students will be able to:

● Understand machine learning fundamentals.

● Explain the fundamental building blocks of deep learning network.

●Understand types of architecture model configuration and the rationality behind selecting a certain training model

● Design an architecture and implement the neural network model that will meet a set of functional requirements, and types of data input,

● Train network, tune the network and observe the performance using user interface.

● Save a model and load the model for further inference.

Modules

Expand All
The goal of first day course is to prepare student for deep learning course. Starting with machine learning fundamentals, it can serve as revision to students who familiar with it or as an overview for those who are not equipped with this knowledge. Students will then introduced to neural networks. They will be exposed to the fundamental building blocks of neural networks. Lab environment will be set up on student individual platform. It is a necessity for the lab environment to be set up appropriately so that the following days of hands-on training can go on seamlessly.
By undergoing the first day course, students will get an overview about machine learning. Student will also get a basic understandings about the fundamental blocks of neural networks and have the environment ready for labs training.

The goal of second day course is to introduce two main architecture of neural networks-feedforward neural networks and convolutional neural networks. The two types of network model will be explained in details and use cases for the corresponding model will be elaborated. Labs training for each model will be further establishing the understanding of students.
Students will target on two main commonly used neural network architectures on second day. At the end of the day, students will be equipped with the knowledge to build deep learning model. At the same time, students will able to hands-on on dl4j and data vectorization, deep learning building framework and familiarize with these.

Third day course will focus on analyzing time series data with recurrent neural network. Input data type and the importance of network which can capture the sequential properties will be emphasized. Variations of recurrent neural network will be explained. A few different use cases will be elaborated to understand the wide application of the network.

Students will understand about sequential data analysis using recurrent neural networks. Various use cases and methods to configure sequential data will be comprehend by students at the end of the third day course.

Trainers

See All
Reset

Reviews

0
based on 0 ratings reviews