Course Offerings

Skymind Offers the Following Courses

Course 1: Introduction to Deep Learning: Building Neural Networks Using Deeplearning4J

This class is an essential course for Data Scientists and Machine Learning Engineers looking to use Neural Networks in Production. Deep Learning: Building Neural Networks Using Deeplearning4J provides participants with the information they need to determine which type of Neural Network is best suited for the task and how to configure, train, evaluate and deploy the Neural Network using Java. Course duration is 3 days and includes hands on Labs as well as Lecture.

Course Duration

3 days and includes hands on Labs as well as Lecture.

Who Should Attend?

This class is suited for Data Scientist and Data Analysts wishing to take advantage of recent breakthroughs in the field of Deep Learning.

Course Prerequisites

Attendees with some programming experience will benefit the most from this course. The labs and Neural Networks will be built using Java using DeepLearning4J and IntelliJ but Python coders and SQL users are welcome.

Class Agenda

This three-day hands-on class will cover the topics listed below.

  • Introduction to DeepLearning
    • Machine Learning vs DeepLearning
  • Neural Network Basics
  • Neural Network Demo
  • Lab 1: Simplest Neural Network Lab
  • The DeepLearning4J Training UI
  • Neural Network Internals
  • Tuning a Neural Network
  • Types of Neural Networks
    • Feed Forward Neural Networks
    • Convolutional Neural Networks
    • Recurrent Neural Networks
  • DL4J Internals
    • DataVec for ETL
    • ND4J for tensor processing
    • DeepLearning4J for building and configuring Neural Networks
    • ND4J backends
  • Feed Forward Neural Networks
    • Uses of Feed Forward Neural Networks
    • LAB: building a FeedForward Neural Network
  • Ingesting Text Data
  • Recurrent Neural Networks
    • Uses of Recurrent Neural Networks
    • Lab: generating weather forecasts using a RNN
    • Lab: Classifying Sequence Data
  • Convolutional Neural Networks
    • Uses of Convolutional Neural Networks
    • Lab: Convolutional Neural Network for image classification
  • Deep Learning in Production
    • Paths to Production
    • Using GPU's
    • Distributed Training
    • Saving and Loading Trained Models
    • Early Stopping

Course 2: Deep Learning Paths to Production with Keras and DL4J

This class is an essential course for Data Scientists and Machine Learning Engineers looking to use Neural Networks in Production. Deep Learning Paths to Production with Keras and DL4j provides participants with the skills and tools needed to take a Deep Learning model from Prototype to successful Production Deployment.

Overview

This class is the best preparation to meet the real-world challenges with a combination of Python and Java. Course duration is two days and includes hands-on practical Labs. It will cover utilization of popular Deep Learning Frameworks and tools, such as Keras, Tensorflow, DeepLearning4j (DL4J,) along with supporting tools like Apache Spark.

What you will learn

In this class you will learn how to:

  • Develop, Train, and Serve a model utilizing Keras and DL4J
  • Select and Configure the appropriate Keras Backend
  • Serialize a trained Python model to storage and load that model into DL4J
  • Apply Transfer Learning per a Pretrained model, Fine-Tuning the Network for the target use case
  • Parallelize a network using Distributed Hardware (CPUs and GPUs)

Audience and Prerequisites

Prerequisites

This class requires that the attendees have an understanding of the core Machine Learning and Deep Learning concepts. Familiarity with Java is preferred.

Audience

This class is suited for practitioners looking to take deep learning models from research into an enterprise production environment.

Course 3: Neural Networks for Time Series Analysis Using Deeplearning4J

Recurrent neural networks have proven to be very effective at analyzing time series or sequential data, so how can you apply these benefits to your use case? Attend this class and learn how to use Long Short Term Memory Neural Networks (LSTM’s) to classify and generate sequences.

Who Should Attend?

This class is suited for Data Scientist and Data Analysts wishing to take advantage of recent breakthroughs in the field of Deep Learning.Knowledge of a programming language is preferable. Labs are performed in Java.

Course Prerequisites

Attendees with some programming experience will benefit the most from this course. The labs and Neural Networks will be built using Java using DeepLearning4J and IntelliJ but Python coders and SQL users are welcome.

Class Agenda

This two-day hands-on class will cover the topics listed below.

Day 1

  • Introduction to neural networks and an overview of the different types of neural networks (feed forward, convolutional, and recurrent)
  • Choosing the appropriate neural network for time series data
  • Hands-on lab: Generating weather forecasts with a recurrent neural network

Day 2

  • Configuring a data ingestion pipeline sequence data
  • Recurrent neural nets for the prediction of medical outcomes
  • Recurrent neural nets for the classification of sequence data
  • Hands-on lab: Sequence classification with recurrent neural networks
  • Hands-on lab: Predicting medical outcomes using recurrent neural network

Course 4: Image Classification with Convolutional Neural Networks and Transfer Learning

Convolutional Neural Networks have achieved greater than human accuracy when classifying images. Attend this class and learn how to apply Convolutional Neural Networks to your data challenges.

Who Should Attend?

This class is suited for Data Scientist and Data Analysts wishing to take advantage of recent breakthroughs in the field of Deep Learning.

Course Prerequisites

Attendees with some programming experience will benefit the most from this course. The labs and Neural Networks will be built using Java using DeepLearning4J and IntelliJ but Python coders and SQL users are welcome.

Class Agenda

This two-day hands-on class will cover the topics listed below.

  • Neural Network Basics
  • Neural Network Demo
  • Lab 1: Simplest Neural Network Lab
  • The DeepLearning4J Training UI
  • Neural Network Internals
  • Convolutional Neural Network Internals
  • Lab: Convolutional Neural Network for image classification
  • Transfer Learning, leveraging a pre-trained model for alternate use
  • Lab2: Transfer Learning Lab
  • Using a Convolutional Neural Network for Non-image Data
  • Lab3: Convolutional Neural Network for Non-image Data

Course 5: Natural Language Processing using Neural Networks

Neural Networks have achieved great success processing written language and speech. In this class you will learn how to use a Neural Network and associated tools to analyze text input or generate text output.

Who Should Attend?

This class is suited for Data Scientist and Data Analysts wishing to take advantage of recent breakthroughs in the field of Deep Learning.

Course Prerequisites

Attendees with some programming experience will benefit the most from this course. The labs and Neural Networks will be built using Java using DeepLearning4J and IntelliJ but Python coders and SQL users are welcome.

Class Agenda

This two-day hands-on class will cover the topics listed below.

  • Neural Network Basics
  • Processing Text as a Sequence of Characters
  • Lab: Weather Forecast Generation using an LSTM
  • Bag of words
  • NGrams
  • Processing Text as a Sequence of Words
  • Lab: Text Processing
  • Word2Vec, using the word association matrix
    • SkipGram
    • Continuous Bag of Word (CBOW)
  • Sentiment Analysis
  • Lab: Generating Realistic Reviews based on a training set.
  • Sequence to Sequence, how a translator would function

Get in touch with our dedicated team

Learn more about the record-breaking power of deep learning.

TALK TO A SKYMIND EXPERT