Learning by doing
Trainers with practical experience
Detailed course material
Clear content description
Tailormade content possible
Training that proceeds
In the course Machine Learning with TensorFlow participants learn to implement machine learning and deep learning applications with the open source TensorFlow framework. TensorFlow comes from Google and uses Python. With TensorFlow you can train and implement neural networks for number classification, image recognition and other problems.
The course Machine Learning with TensorFlow starts with an overview of the basic principles of Machine Learning and an explanation of the differences of Supervised, Unsupervised and Deep Learning. The data types of TensorFlow like vectors, arrays, lists and scalars are treated and the Colab and DataBricks development environments are discussed.
Subsequently the Machine Learning with TensorFlow course pays attention to the central Tensor Data Structure, which can be regarded as a container in which data in N dimensions can be stored. Rank, shape and type of tensors are discussed and TensorFlow operations and sessions are also treated.
Special attention is given to neural networks in which both Convolutional and Recurrent Neural Networks are explained. Convolution and Pooling, making connections between Input Neurons and Hidden Layers are also discussed.
The Visualization of models with TensorBoard is also part of the Machine Learning with TensorFlow course. Supervised Learning with Linear and Logistic Regression are reviewed and Ensemble techniques and Gradient Boosting are explained.
In addition the course Machine Learning with TensorFlow deals with Natural Language Processing with tokenization and text classification. Spam detection serves as an example and also Deep Learning is on the course schedule.
Various TensorFlow Optimizers such as Stochastic Gradient Descent, Gradient clipping and Momentum are discussed as well. And also Image Processing with Dimensionality Reduction and using the Keras APIs is covered.
Finally the course Machine Learning with TensorFlow ends with a discussion of models in production. Models as REST Service and Keras Based Models are treated.
The course Machine Learning with TensorFlow is intended for data scientists who want to use Python and the TensorFlow machine learning libraries to make predictions based on models.
To participate in this course knowledge of and experience with Python is required and knowledge of data analysis libraries such as Numpy, Pandas and Matplotlib is desirable.
The theory is discussed on the basis of presentations. Illustrative demos clarify the concepts. The theory is interchanged with exercises. The Anaconda distribution with Jupyter notebooks is used as a development environment. Course times are from 9:30 to 16:30.
After successful completion of the course participants receive an official certificate Machine Learning with TensorFlow.
Module 1 : Intro TensorFlow
Module 2 : Tensor Data Structure
Module 3 : Neural Networks
What is TensorFlow?
Colab and Databricks
Vectors and Scalars
Arrays and Lists
Rank, Shape and Type
Variables and Constants
What are Neural Networks?
Convolutional Neural Networks
Multiple Layers of Arrays
Local respective fields
Convolution and Pooling
Connecting Input Neurons
Recurrent Neural Networks
Module 4 : Tensor Board
Module 5 : Supervised Learning
Module 6 : Natural Language Processing
Data Flow Graph
High Level Blocks
High Degree Nodes
Sequence Numbered Nodes
Keras and TensorFlow
Deep Learning Model
Module 7 : TensorFlow Optimizers
Module 8 : Image Processing
Module 9 : Models in Production
Stochastic Gradient Descent
Fully Connected Layer
Model as REST Service
Keras Based Models
All our courses are classroom courses in which the students are guided through the material on the basis of an experienced trainer with in-depth material knowledge. Theory is always interspersed with exercises.
We also do custom classes and then adjust the course content to your wishes. On request we will also discuss your practical cases.
The course times are from 9.30 to 16.30. But we are flexible in this. Sometimes people have to bring children to the daycare and other times are more convenient for them. In good consultation we can then agree on different course times.
We take care of the computers on which the course can be held. The software required for the course has already been installed on these computers. You do not have to bring a laptop to participate in the course. If you prefer to work on your own laptop, you can take it with you if you wish. The required software is then installed at the start of the course.
Our courses are generally given with Open Source software such as Eclipse, IntelliJ, Tomcat, Pycharm, Anaconda and Netbeans. You will receive the digital course material to take home after the course.
The course includes lunch that we use in a restaurant within walking distance of the course room.
The courses are planned at various places in the country. A course takes place at a location if at least 3 people register for that location. If there are registrations for different locations, the course will take place at our main location, Houten which is just below Utrecht. A course at our main location also takes place with 2 registrations and regularly with 1 registration. And we also do courses at the customer’s location if they appreciate that.
At the end of each course, participants are requested to evaluate the course in terms of course content, course material, trainer and location. The evaluation form can be found at https://www.klantenvertellen.nl/reviews/1039545/spiraltrain?lang=en. The evaluations of previous participants and previous courses can also be found there.
The intellectual property rights of the published course content, also referred to as an information sheet, belong to SpiralTrain. It is not allowed to publish the course information, the information sheet, in written or digital form without the explicit permission of SpiralTrain. The course content is to be understood as the description of the course content in sentences as well as the division of the course into modules and topics in the modules.