Posted on March 4, 2024 by Yash Sutrave -
- The AI Revolution: 1950’s to now
- Generative AI: Real-World Applications
- Content generation
- Business development
- Client delivery
- Training
- Try Cprime’s AI Chat Bot: On your laptop, tablet, or phone
- Chained prompts
- Strong verbs
- Summarize or expand responses
- Focus for an audience or channel
- … and much more
- What more you can do: APIs, Plugins, and Vectors – Oh my!
- A secure AI
- Leverage your own data
- Import and data or website you need
Posted on September 28, 2023 by Yash Sutrave -
Part 1: Introduction
- Workshop Objectives & Attendee Pain Points
- Demystifying AI: From Myth to Reality
Part 2: Technology & Terminology Primer
- Breaking Down AI: Essential Terms and Concepts
- Linking AI to Business Operations
Part 3: Pitfalls of AI Adoption
- Common Challenges: Data Quality, Scalability, and Integration
- Addressing Ethical and Bias Concerns
Part 4: ROI Analysis for AI Initiatives
- Quantifying AI's Real-World Business Value
- Decoding the Real-World Value of AI for Your Business
- Practical Steps for Measuring AI Impact
Part 5: Map AI Solutions to Customer’s Business
- From Current Pain Points to Potential AI Solutions
- Assessing existing systems, databases, and software
- Identifying communication and integration gaps
- AI as a solution to streamline and optimize
- Strategies for Effective Data Management with AI Integration
Part 6: Conclusion
- Aligning AI with Long-Term Goals & Future Steps
Appendix: Selected AI Solutions Deep Dive
- Resources and Best Practices for Implementation
Posted on May 30, 2023 by Yash Sutrave -
Part 1: ChatGPT Basics & Underlying Concepts
We begin by spending just a little time describing ChatGPT and defining relevant terminology to set the stage for learning. The Q&A allows learners to quickly confirm their understandings so we can get to the fun and interesting part, using this tool.
- Definitions
- Types of GPTs (Chat & others)
- The role of data (and your company’s data)
- What ChatGPT is good at (and not good at)
- Who can use ChatGPT (and for what)?
- Q&A
Part 2: Interacting with ChatGPT
Most of our time in this short course is spent interacting with ChatGPT. Each of the sub-sections below introduces a specific usage mode, and includes:
- Examples – The instructor shows multiple examples of that usage mode.
- Play-time – Learners are allowed time to try their hand with that usage mode on their own.
- Show and Tell – Learners share and discuss their experiences with that usage mode with each other and get feedback from the instructor.
Converse with ChatGPT
We start with the most basic interactions with ChatGPT:
- Ask questions
- Use chained prompts (and break chains when needed)
- Use strong and weak verbs in prompts.
- With Examples, Play-time, Show and Tell
Prompt ChatGPT to tailor its response
ChatGPT’s responses will sometimes not meet your needs. They may be too long and verbose, too short and cryptic, or not laid out in a useful way. So, we will look at various ways to ask it to provide or restate its response in more appropriate ways.
- Summarize long responses
- Expand on short responses
- Format responses (e.g., bulleted or numbered lists, headings, etc.)
- Provide an example of content & format you want it to respond with
Prompt ChatGPT to use appropriate roles
We will look at how to focus ChatGPT’s interactions with you based on role definitions.
- Provide responses appropriate for a particular role or audience
- Provide responses appropriate to a channel (e.g. social media)
- Play a role in how it responds
- Role-play with you
Prompting ChatGPT to respond with questions
ChatGPT can do more than just answer questions. We will look at how to prompt it to ask questions as well.
- Prompt it to provide questions (e.g. for an interview)
- Prompt it to ask clarifying questions before responding
Providing data to ChatGPT
The free public version of ChatGPT cannot access data. So, we will look at ways you can provide it with the data you want it to use in its responses.
- Loading the prompt with data
- Providing data in multiple prompts for a single response
- With Examples, Play-time, Show and Tell
Part 3: Advanced Use Cases & Interactions
Connecting ChatGPT to other applications
We will explore a variety of tools that can be used to connect applications to the paid version of ChatGPT.
- Plug-ins for commercial applications (e.g. Excel) to use ChatGPT
- ChatGPT’s API for writing your own plug-ins or adding ChatGPT capabilities to your company’s applications
Making data available to ChatGPT
We will explore a variety of ways to enable ChatGPT to use other data.
- Plug-ins for ChatGPT to access external data sources (e.g. Wikipedia)
- Tools to feed large data sets into ChatGPT’s prompts
- Using a private LLM (Large Language Model) to enable ChatGPT to use specialized language and terminology
- Grounding ChatGPT on your company’s data
Part 4: Class wrap-up and Q&A
Posted on November 5, 2020 by Yash Sutrave -
Posted on October 23, 2020 by Yash Sutrave -
Part 1: What is BI?
We’ll start out by covering business intelligence basics to lay the groundwork for an intelligent approach to reporting and visualizing data.
- Business Intelligence Overview
- Common Challenges
- Benefits of Power BI
Part 2: Getting started with Power BI
Power BI is an extensive toolbox for working with and analyzing data. We’ll cover the fundamentals of the service, how Power BI’s features are organized, and immediately orient towards dashboards and visualization.
- Overview & Pricing/Licensing
- Components of Power BI
- Building Blocks of Power BI
- Quick Tour of Power BI Service
Part 3: Building simple reports
Reports are the first step in graphically communicating information related to your data. In this section of the class, you’ll learn to use and navigate the types of datasets you encounter every day, and how to use them to begin shaping meaningful communication.
- Importing excel data
- Using preexisting datasets
- Creating visualizations
- Using slicers
Part 4: Dashboards
In this section, we’ll cover how to create and use dashboards for common needs. By the end of this section, you’ll understand what’s realistic to expect from your PowerBI dashboards and how to set them up, share them, and produce valuable insights with your team quickly.
- Dashboard expectations vs. features
- Using KPI
- Create and Configure a Dashboard
- Shared Dashboards with your Organization
- Pinning visuals
Part 5: Exploring data
In this final section of class, we’ll get a bit more granular about navigating, analyzing and communicating about your data. By the time we conclude, you’ll be ready to start applying what you’ve learned in your own real-world situations.
- Use Quick Insights
- Display Visuals and Tiles Full-Screen
- Edit Tile Details
- Get More Space on Your Dashboard
- Ask Questions of your Data with Natural Language
- Advanced Navigation
Posted on October 17, 2020 by Yash Sutrave -
*All lab exercises are run in a Linux environment. A Windows environment can be provided upon request.
Part 1: Introduction to Splunk
- What’s Splunk?
- Authentication Methods
- Access Controls & Users
- Products, Licensing, and Costs
- Quick Tour Guide: User Interface
- Exercise: Lab Environment and Configuration
Part 2: Indexes
- Splunk Data
- What are Indexes?
- What are Indexers?
- Exercise: Create Your First Index
- Search-Head
- Index Clusters
- Index Pipeline
- Exercise: Upload Data Manually
- Events
- Fields & Field Extraction
- Exercise: Using the Field Extractor Tool
- Forwarders
- Metrics
- Exercise: Using the Forwarder to Send Data
- Removing Data
Part 3: Splunk Architecture
- Components of Splunk Deployments
- Deployment Scenarios
Part 4: Search Processing Language
- What is Search Processing Language (SPL)?
- Searching Operators
- Search Commands
- Search Pipeline
- Exercise: Search Examples
- Subsearches
- Commonly Used Search Commands
- Exercise: Search Examples II
- Drilldowns
- Lookups
- Exercise: Using Lookups
- Optimize Searches
- Exercise: Search Examples III
Part 5: Dashboard & Visualizations
- Dashboards in Splunk
- Creating Dashboards
- Visualization Types
- Search as Reports
- Dashboards
- Exercise: Creating a Dashboard
- Drilldown
- Forms
- Exercise: Add Input Forms
- Exercise: Drilldown
Part 6: Alerts
- Creating Alerts
- Scheduling Alerts
- Alerts Notifications
- Exercise: Creating Alerts
Part 7: Scheduled Reports
- Creating Scheduled Reports
- Exercise: Create a Scheduled Report
Part 8: Putting All Pieces Together
Exercise: As a final lab, you’ll configure a typical scenario when using Splunk. You'll install and configure an NGINX, then the Splunk forwarder to collect logs in Splunk. The idea is that you can apply everything you've learned within the Bootcamp: creating searches, visualizations, dashboards, etc.
Posted on October 17, 2020 by Yash Sutrave -
Posted on October 17, 2020 by Yash Sutrave -
Part 1: Foundations
Start from zero. Build the vocabulary and mental models everything else depends on.
Module 1: What AI actually is, minus the hype
- AI vs. ML vs. deep learning
- Models, parameters, weights, training vs. inference
- Supervised, unsupervised, reinforcement learning
- Where AI is already running inside your company, whether approved or not.
Module 2: Neural networks and transformers
- Neurons and layers for engineers, not mathematicians
- Why transformers replaced everything before them
- Attention, explained so it clicks
- Training vs. running a model
- Why the cost profiles differ wildly.
Module 3: Inside a large language model
- Tokenization, and why it explains half the weird behavior you have seen
- Embeddings
- Context windows and the constraints they put on your design
- Temperature and sampling: the dials you will actually turn
- Why models hallucinate, and what that means for what you are allowed to build
By the end of Part 1 you can read any AI claim, vendor pitch, or job posting and know exactly what is being said, and predict where a model will fail before you write code.
Part 2: The Big Data Prerequisite
- Evaluating your big data practice
- State of tools – understanding intelligent big data stacks
- Visualization and Analytics
- Computing
- Storage
- Distribution and Data Warehousing
- Strategically restructuring enterprise data architecture for AI
- Unifying data engineering practices
- Datasets as learning data
- Defeating Bias in your Datasets
- Optimizing Information Analysis
- Utilizing the IoT to amass a large amount of data
Part 3: Implementing Machine Learning
- Examine pillars of a practicing AI team
- Business case
- Domain expertise
- Data science
- Algorithms
- Application integration
- Bettering Machine Learning Model Management
- State of tools – understanding intelligent machine learning stacks
- Machine Learning Methods and Algorithms
- Decision Trees
- Support Vector Machines
- Regression
- Naïve Bayes Classification
- Hidden Markov Models
- Random Forest
- Recurrent Neural Networks
- Convolutional Neural Networks
- Developing Validation Sets
- Developing Training Sets
- Accelerating Training
- Encoding Domain Expertise in Machine Learning
- Automating Data Science
- Deep Learning
Example: TensorFlow – We will take a look at Google’s TensorFlow as a tool for integrating machine learning features. We’ll come away from the exercise with an understanding of the programming skills needed to leverage TensorFlow and the impacts of normal application workflow.
Part 4: Creating Concrete Value
- Opportunities for automation
- Understanding automation vs. job displacement vs. job creation
- Finding hidden opportunities through improved forecasting
- Production and operations
- Adding AI to the Supply Chain
- Marketing and Sales Applications
- Predict Customer Behavior
- Target Customers Efficiently
- Manage Leads
- AI-powered content creation
- Enhancing UX and UI
- Next-Generation Workforce Management
- Explaining Results
Use case breakout: Scoring the criteria for three potential applications. In groups, we’ll evaluate application use cases for machine learning: Medical imaging, electronic medical records, and genomics. We’ll grade each use case based on a scorecard for the following:
- Quantity of data
- Quality of data
- ML techniques
Posted on October 17, 2020 by Yash Sutrave -
Part 1: Data and Information
- Data in the Real World
- Data vs. Information
- The Many “Vs” of Data
- Structured Data and Unstructured Data
- Types of Data
Part 2: Data Analysis Defined
- Why do we analyze data?
- Data Analysis Mindset
- Data Analysis Steps
- Data Analysis Defined
- Descriptive Statistics vs Inferential Statistics
Part 3: Types of Variables
- Categorical vs Numerical
- Nominal Variables
- Ordinal Variables
- Interval Variables
- Ratio Variables
Part 4: Central Tendency of Data
- (Arithmetic) Mean
- Median
- Mode
Part 5: Basic Probability
- Probability Uses In Business
- Ways We Can Calculate Probability
- Probability Terms
- Calculating Probability
- Calculating Probability from a Contingency Table
- Conditional Probability
- Frequency Distribution
Part 6: Distributions, Variance, and Standard Deviation
- Discrete Distributions
- Continuous Distributions
- Range
- Quartiles
- Variance
- Standard Deviation
- Population vs. Sample
- Application of the Standard Deviation
- Standard Deviation and the Normal Distribution
- Sigma (σ) Values (Standard Deviations)
- Bimodal distribution
- Skew and Summary
- Other Distributions
- Poisson Distribution
- Exponential Distribution
- Pareto Distribution (“80/20”)
- Log Normal Distribution
- Distributions in Excel
Part 7: Fitting Data
- Bivariate Data (Two Variables)
- Covariance and Correlation
- Simple Linear Regression
- Linear Regression
- Fitting Functions
- Linear Fit
- Polynomial Fit
- Power-Law Fit
Part 8: Predictive Analytics Overview
- Monte Carlo Method
Posted on October 17, 2020 by Yash Sutrave -
Part 1: The Value and Challenges of Data-Driven Disruption
- Objectives and expectations
- Hurdles to becoming a data-driven organization
- Data empowerment
- Instilling data practices in the organization
- The CRISP-DM model of data projects
Part 2: Tying Data to Business Value
- What constitutes data-driven value
- Requirements gathering: How to approach it
- Kanban for data analysis
- Know your customers
- Stakeholder cheat sheets
- EXERCISE: Data-driven project checklist
- LAB: Data analysis techniques: Aggregations
Part 3: Understanding Your Data
- Data defined
- Data versus information
- Types of data
- Unstructured vs. Structured
- Time scope of data
- Sources of data
- Data in the real world
- The 3 V’s of data
- Data Quality
- Cleansing
- Duplicates
- SSOT
- Field standardization
- Identify sparsely populated fields
- How to fix common issues
- LAB: Prioritizing data quality
Part 4: Analyzing Data
- Analysis foundations
- Comparing programs and tools
- Words in English vs. data
- Concepts specific to data analysis
- Domains of data analysis
- Descriptive statistics
- Inferential statistics
- Analytical mindset
- Describing and solving problems
- Averages in data
- Mean
- Median
- Mode
- Range
- Central tendency
- Variance
- Standard deviation
- Sigma values
- Percentiles
- Demystifying statistical models
- Data analysis techniques
- LAB: Central tendency
- LAB: Variability
- LAB: Distributions
- LAB: Sampling
- LAB: Feature engineering
- LAB: Univariate linear regression
- LAB: Prediction
- LAB: Multivariate linear regression
- LAB: Monte Carlo simulation
Part 5: Thinking Critically About Your Analysis
- Descriptive analysis
- Diagnostic analysis
- Predictive analysis
- Prescriptive analysis
Part 6: Data Analysis in the Real World
- Deployment of analyses
- Best practices for BI
- Technology ecosystems
- Relational databases
- NoSQL databases
- Big data tools
- Statistical tools
- Machine learning
- Visualization and reporting tools
- Making data useable
Part 7: Data Visualization & Reporting
- Best practices for data visualizations
- Visualization essentials
- Users and stakeholders
- Stakeholder cheat sheet
- Common presentation mistakes
- Goals of visualization
- Communication and narrative
- Decision enablement
- Critical characteristics
- Communicating data-driven knowledge
- Formats and presentation tools
- Design considerations
Part 8: Hands-On Introduction to R and R Studio
- What is R?
- LAB: Intro to R Studio
- LAB: Univariate linear regression in R
- LAB: Multivariate linear regression in R
