Course 1: Visualizing and Describing Data

A picture is worth a thousand words and data! This course compares various visualization tools and stresses the significance of collecting and selecting data properly. It also emphasizes the essential aspects of designing an effective data collection process and validating the information's quality for analysis.

This course will enable you to: 

• Understand and plan the lifecycle of a data analysis project

• Assess data quality for analysis and reporting

• Differentiate between Big Data and Sampling results

• Compare Probabilistic and Non-probabilistic sampling techniques

• Transform any business into a comprehensive database

• Visualize variables effectively and intelligently

• Explain and interpret data using complete descriptive statistics

• Understand and interpret estimations based on sample results 

• Apply these skills using SAS-Viya and Python  

The course covers the essentials of data analytics and provides participants with a comprehensive understanding of data structuring for efficient analysis, statistical tests, and technology tools. It also addresses issues related to improper data for analysis, sample size determination, and the advantages and disadvantages of Big Data solutions.

This course will enable you to: 

• Understand the logic of hypothesis tests

• Differentiate between prior and posterior errors

• Benchmark sample statistics against standard references

• Differentiate between profiling and describing groups

• Identify variables that profile groups

• Explore the complete story behind simple regression

• Distinguish the use of linear and non-linear regression methods

• Consolidate all analytics into one smart chart

• Apply these concepts using SAS-Viya and Python. 

All business applications, data analysis solutions, and AI algorithms rely on seamless data access. Effective data governance and management strategies are crucial to control, unify, and leverage diverse data from various sources for efficient usage. Data governance establishes policies and procedures to ensure data availability, usability, safety, storage, and correctness, while data management executes these policies for managerial decision-making. This course covers practices for collecting, organizing, protecting, storing, and accessing data for business decisions across industries.

This course will enable you to: 

• Understand the requirements of data assets 

• Design a data architecture and plan short and long-term database projects 

• Understand database design concepts 

• Collect, process, validate, and store data 

• Manage databases and data warehouses 

• Protect, secure data, and ensure data privacy 

• Govern data accessibility 

The foundation of AI solutions for decision-making, "Supervised" ML models are now within reach for any practitioner thanks to rapid technological advancements. Mastering essential predictive models has become more achievable, particularly with the improvement of automation tools. This course provides a comprehensive overview of "supervised" Machine Learning algorithms and their significance in improving predictions across various industries.

 This course will enable you to: 

• Learn about the rise of AI in conjunction with IoT and technological capabilities

• Understand the true meaning of Machine Learning (ML)

• Establish the connection between Data Analysis and Machine Learning

• Enhance predictions by experimenting with different ML models

• Refine classifications with models using multiple variables simultaneously

• Compare models using accuracy measures

• Grasp the usefulness of various cross-validation techniques

• Apply these concepts using SAS-Viya and Python. 

How can we uncover the hidden patterns in complex data sets? Dimension reduction techniques like PCA or t-SNE simplify multiple variables into easy-to-understand "maps," which help reveal relationships between them. This allows for better decision-making. This approach distinguishes scientific "clustering" from common sense "filtering," enabling the identification of market niches through data analysis profiling techniques.

This course will enable you to: 

• Understanding exploratory analysis

• Discovering hidden patterns within data sets

• Mastering all "pattern finding" algorithms used in AI applications

• Mapping complex data sets of multiple variables in simple charts

• Evaluating the quality of reduced multidimensionality solutions

• Differentiating between clustering and filtering

• Running professional segmentation with intelligent clustering

• Applying it all using SAS Viya and Python  

This course covers the challenges of Big Data technologies, including capturing, storing, analyzing, sharing, and querying data. It also compares traditional structured data with new, large, complex, and unstructured data, and explains how to design a Big Data implementation plan and develop strategies for data-driven solutions using analytics-focused architectural diagrams. In summary, the course explores the five steps of Big Data processing: data sources, acquisition, storage, analysis, reporting, and visualization.

This course will enable you to: 

• Plan and implement a Big Data project

• Design a Big Data architecture diagram including structure and technologies

• Gain hands-on experience with popular Big Data storage and computing systems

• Create a relevant architecture diagram for analytics tasks using Azure - Databricks

• Understand Big Data Architectures and Paradigms: Hadoop, MPP, Distributed In-memory

• Learn about Big Data Compute Technologies like Hadoop, MapReduce, Spark, Kafka, etc.

• Bridge the gap between data projects and organizational needs 

The rise of AI and the fourth technological revolution can be attributed to various factors, with deep learning playing a central role. This wide-ranging science has enabled automation in numerous industries, including healthcare, security, manufacturing, engineering, education, the oil industry, marketing, and more. It has facilitated the development of solutions for self-driving cars, bots, and other applications. This course will delve into the main algorithms driving this technological breakthrough.

This course will enable you to: 

• Understand the mathematics behind Deep Learning

• Explore the logic of optimization using Gradient Descent

• Break down the components of neural networks

• Adjust algorithm hyperparameters to optimize cost functions

• Explore the architecture of major deep learning networks

• Enhance the accuracy of Classification and Estimation

• Gain knowledge in image classification, face recognition, and object detection

• Apply deep learning algorithms to solve new challenging problems 

This advanced course introduces the principles and techniques behind models that can generate new data, such as images, text, or music, rather than just recognizing or classifying existing data. It typically covers the theory and practice of generative models and explores how deep learning can be used to learn data distributions and create new, realistic samples.

 This course will enable you to: 

• Understand the basics of Deep Learning

• Gain a full understanding of Generative Adversarial Networks (GANs)

• Fine-tune Autoencoders (AEs)

• Explore Variational Autoencoders (VAEs)

• Learn how to use Recurrent Generative Models

• Implement Data Augmentation & Synthetic Data

• Consider Ethics and Bias in Generative Models

• Work on real projects

• Apply everything using TensorFlow 

Natural Language Processing (NLP) is a field of AI that involves processing text in order to extract information from human language. NLP enables computers to understand and interpret natural language, similar to how humans do. This course covers the steps involved in preprocessing text, relevant coding, and essential generative AI tools that are important for data scientists and AI practitioners.

This course will enable you to:

• Preparing and vectorizing data

• Building word embedding and text generation models

• Understanding multinomial and Gaussian generative models

• Exploring all the components of a successful chatbot and Robotic Process Automation

• Tokenizing sentences and creating a Stop Words dictionary

• Stemming and lemmatizing words, Parts of Speech, and Name Entity Recognition

• Using Bag of Words and TF-IDF, Word-Term matrix

• Topic Modeling with Latent Dirichlet Allocation (LDA) model

• Word Embeddings with word2vec: CBOW and SKIPGRAM methods