• Familiarity with the Python programming language.
• An understanding of basic programming and computer science concepts, including program flow, loops, and functions.

In this course participants will learn:

• What machine learning is and how it is different from traditional programming approaches to solving problems.
  • We will cover an overview of the field as a whole and the subtypes of problems studied in machine learning
• How to evaluate machine learning models.
  • We will go over common evaluation metrics and discuss when and why each one is appropriate.
• How to set up data for training and testing, including different ways of splitting the data and what pre-processing steps are commonly needed.

• The machine learning workflow
• How features are used in machine learning
• The difference between supervised and unsupervised learning
• The difference between regression and classification
• Evaluation metrics for regression and classification

• Introduction to scikit-learn
• Common cleaning and pre-processing steps
• Splitting Data in to train and test sets
• Error Analysis

In this course participants will learn:

• How machine learning differs from standard programmed solutions.
• The different types of machine learning algorithms, what problems they are meant to solve, and how to evaluate the different algorithms.
• What steps are needed to begin work on a machine learning problem, including cleaning and other pre-processing steps.

• An overview of supervised learning algorithms and examples of how to use them in the scikit-learn library.
• An overview of the unsupervised learning algorithms and examples of how to use them from scikit-learn library.
• How to integrate machine learning models in an enterprise environment, including an overview of complementary technologies.

• What is Machine Learning?
• Supervised and Unsupervised Learning
• Evaluation of Machine Learning Algorithms
• Pre-processing steps
• Linear Regression
• Logistic Regression
• Decision Trees
• Random Forest

• K-means Clustering
• Gaussian-based clustering
• Dimensionality Reduction with PCA
• DBSCAN for Anomaly Detection
• Local Outlier Factor
• Isolation Forest
• Using Flask to deploy models
• Using Spark to run models over big data

• Familiarity with the Python programming language.
• An understanding of basic programming and computer science concepts, including program flow, loops, and functions.
• Basic Familiarity with the pandas Python library.

In this course, participants will learn:

• What supervised learning is and what types of problems it can solve.
• Common supervised learning algorithms, their differences, and how to use these algorithms.
• Common concerns to consider when using supervised models, such as sample vs population differences, bias, and variance.

• Introduction to Supervised Learning
• Linear Regression
• Logistic Regression
• Support Vector Machines
• k-Nearest Neighbors

• Decision Trees
• Random Forests
• Gradient-Boosted Trees
• Sample vs population concerns
• The bias/variance trade-off

• Familiarity with the Python programming language.
• An understanding of basic programming and computer science concepts, including program flow, loops, and functions.
• Basic Familiarity with the pandas Python library.

In this course, participants will learn:

• The common subtypes of unsupervised learning and what type of exploration they are useful for.
• Different clustering algorithms and distance calculations and when each one might be useful.
• How dimensionality reduction works and its use in both visualization and feature extraction.
• How anomaly detection can be used to find instances that stick out statistically, even with out knowing any labels.

• Introduction to unsupervised learning
• Distance measures in high-dimensional spaces
• K-Means clustering
• Hierarchal clustering
• Gaussian-based clustering

• Dimensionality Reduction uses
• Principal Component Analysis
• DBSCAN for Anomaly detection
• Local Outlier Factor
• Isolation Forest

• An understanding of basic programming, including control flow, loops, and functions, as well as a familiarity with the basics of computer science like computer architectures.
• Familiarity with the Python programming language.

In this course, participants will learn:

• The basics of PySpark including the Hadoop environment and HDFS basics, the resilient distributed dataset (RDD) and its manipulation, and DataFrames.
• How to aggregate data at scale using SparkSQL write User Defined Functions (UDFs), optimization strategies for PySpark, and how to configure the environment for performance.

Introduction to PySpark

• Hadoop and HDFS basics
• PySpark Overview
• Resilient Distributed Datasets (RDDs)
• DataFrames
• SparkSQL

Advanced PySpark

• User Defined Functions (UDFs)
• Optimization Strategies
• Data Formats
• Configuring Spark

• Familiarity with the Python programming language.
• An understanding of basic programming and computer science concepts, including program flow, loops, and functions.
• Basic familiarity with machine learning concepts, specifically linear regression and vanilla neural networks (multilayer perceptrons).

In this course, participants will learn:

• The fundamentals of applying deep learning to computer vision. We cover common computer vision paradigms and discuss how deep convolutional neural networks can be applied to them.
  • Image classification
  • Object detection
  • Image segmentation
• How the deep learning components fit into the overall computer vision pipeline

• Convolutional Neural Network basics
• Introduction to various computer vision paradigms
  • Image Classification
  • Single object detection
  • Multiple object detection
  • Image Segmentation

• Real life use cases
• Neural Network Architecture overviews

• Familiarity with the Python programming language.
• An understanding of basic programming and computer science concepts, including program flow, loops, and functions.
• Basic familiarity with machine learning concepts, exposure to the scikit-learn Python library.

In this course, participants will learn:

• The fundamentals of NLP. We cover common tasks lower level tasks and discuss how the information gleaned from them is useful. We will use common Python libraries to show how this processing can be done.
• Higher level common applications in NLP, their uses, and their potential drawbacks. We will discuss what the training data looks like for each application, some applicable algorithms, and libraries that implement these algorithms.
• The basics of deep learning for NLP and what deep learning can do for NLP. Almost all NLP uses deep learning in some format or another, but you do not have to be a deep learning expert to use the techniques!

Introduction to NLP Concepts and Applications

• Part of Speech Tagging
• Named Entity Recognition
• Tokenization
• Lemmatization
• Text Classification
• Topic Modeling
• Sentiment Analysis
• Information Extraction
• Using the Python Libraries Spacy and Gensim

Introduction to Deep Learning in NLP

• Word Vectors
• Sentence Embeddings
• Machine Learning over Deep Representations of of Language

• Familiarity with the Java programming language.
• An understanding of basic programming and computer science concepts, including program flow, loops, and functions.

This course provides and in-depth introduction to Apache Accumulo. It is aimed at developers, administrators, and managers who will be implementing solutions using Accumulo. The course uses hands-on development to reinforce the material. Accumulo’s background and storage design enable developers to create efficient data structures enabling datasets to scale to trillions of records and hundreds of petabytes. A deep dive into System administration allows administrators to create a secure and robust system with performance that scales linearly. Managers will also gain insight on the benefits of using Accumulo and the ability to transition from RDBMS to NoSQL solutions.

Accumulo Introduction and Basics

• Hadoop and Accumulo architecture
• Writing to Accumulo and compactions
• Reading from Accumulo
• Compactions
• Column visibility
• Data layout and schema design
• Locality groups

Accumulo Systems and Administration

• Accumulo Installation
• Accumulo Updates
• Accumulo-wide configuration
• Table administration and table configuration
• RFiles
• Hadoop, HDFS, and YARN considerations
• Accumulo metrics and monitoring
• Tracing
• Accumulo on AWS best practices

Advanced Accumulo Topics and Table Design

• Iterators
• Survey of Accumulo table design and index types

Spark and Accumulo

• Reading from Accumulo with Spark
• Writing to Accumulo from Spark
• Architectural discussion on how Spark and Accumulo work together

Graph Indexing

• Building, querying, and deploying an edge-node graph
• Iterators for graphs in Accumulo

Advanced Accumulo Ingestion

• Advanced discussion on how writes to Accumulo work
• Basic architecture patterns for Ingestion
• Using NiFi to build data flows into Accumulo
• Bulk loading strategies into Accumulo

• Familiarity with the Python programming language.
• An understanding of basic programming and computer science concepts, including program flow, loops, and functions.

In this course, participants will learn:

• Why properly visualizations are crucial in understanding data and sharing that understanding
• The roles that visualization plays in “exploration” vs. “explanation” and how to properly produce visualizations that fit different needs.
• Visualization theory including the choice of visualization and the role that color, styling, and presentation play in conveying specific meanings.
• How to mindfully construct visualizations around considerations like the medium with which it will be shared, color blindness, and prioritizing their key message.

• Visualization use cases
• Demonstration of Python’s plotting capabilities
• Comparison of Python’s plotting libraries

• A deep dive into Matplotlib
• Visualization theory
• Special plotting use cases