Render ATL

Workshops

USEFUL AI - Engineering

WORKSHOP

OUTLINE & REVIEW

  • 8:00 - Intros (30s each)
  • 8:30 - General Overview
  • 9:00 - Demos
  • 9:30 - Basic Coding Challenge
  • 10:00 - Custom Problem
  • 10:30 - About LLMs
  • 11:00 - Q&A - Early Lunch!

1. INTROS

30 Seconds Each

  1. Name & Company
  2. AI Experience
  3. One fun Fact

2. General Overview

Intro AI Fun

  1. Overview
  2. Concepts
  3. Popular AI

Don't Code Algorithms

Let Data Do it For you!

  1. Construct a Model
  2. Show it Data (Train)
  3. Use the neural network model!

WHY NEURAL?

Neural Synapses Are

  • Densely connected
  • Have varying thickness in connections (weights)
  • Vary synapse size (bias)
  • Need a certain amount of electricity to fire, or activation voltage.

Example Problem

XOR operation

A Simple Network

b = -5

a = σ

b = 15

a = σ

b = -15

 

w=10

w=-10

w=10

w=-10

w=10

w=10

A Simple Network

b = -5

a = σ

b = 15

a = σ

b = -15

a = σ

w=10

w=-10

w=10

w=-10

w=10

w=10

0

1

b = -5

a = σ

0.9933

(0 * 10)
+ (1 * 10)
+ -5
= 5
σ(5) = 0.9933

A Simple Network

b = -5

a = σ

b = 15

a = σ

b = -15

a = σ

w=10

w=-10

w=10

w=-10

w=10

w=10

0

1

0.9933

(0 * -10)
+ (1 * -10)
+ 15
= 5
σ(5) = 0.9933

b = 15

 

a = σ

0.9933

A Simple Network

b = -5

a = σ

b = 15

a = σ

b = -15

a = σ

w=10

w=-10

w=10

w=-10

w=10

w=10

0

1

0.9933

(0.9933 * 10)
+ (0.9933 * 10)
+ -15
= 4.866
σ(4.866) ≈ 0.9924

0.9933

b = -15

a = σ

0.9924

DONE!

GPU Speed

Is this the same as code?

Matrix Math

Linear Algebra

\sigma\left(\begin{bmatrix} \begin{bmatrix} 10 & 10 \\ -10 & -10 \end{bmatrix} & \begin{bmatrix} -5 \\ 15 \end{bmatrix} \\ \begin{bmatrix} 10 \\ 10 \end{bmatrix}^T & \begin{bmatrix} -15 \end{bmatrix} \end{bmatrix} \cdot \begin{bmatrix} 0 \\ 1 \\ 1 \end{bmatrix} \right)
\sigma\left(\begin{bmatrix} \begin{bmatrix} 10 & 10 \\ -10 & -10 \end{bmatrix} & \begin{bmatrix} -5 \\ 15 \end{bmatrix} \\ \begin{bmatrix} 10 \\ 10 \end{bmatrix}^T & \begin{bmatrix} -15 \end{bmatrix} \end{bmatrix} \cdot \begin{bmatrix} 0 \\ 0 \\ 1 \end{bmatrix} \right)
\sigma\left(\begin{bmatrix} \begin{bmatrix} 10 & 10 \\ -10 & -10 \end{bmatrix} & \begin{bmatrix} -5 \\ 15 \end{bmatrix} \\ \begin{bmatrix} 10 \\ 10 \end{bmatrix}^T & \begin{bmatrix} -15 \end{bmatrix} \end{bmatrix} \cdot \begin{bmatrix} 1 \\ 0 \\ 1 \end{bmatrix} \right)
\sigma\left(\begin{bmatrix} \begin{bmatrix} 10 & 10 \\ -10 & -10 \end{bmatrix} & \begin{bmatrix} -5 \\ 15 \end{bmatrix} \\ \begin{bmatrix} 10 \\ 10 \end{bmatrix}^T & \begin{bmatrix} -15 \end{bmatrix} \end{bmatrix} \cdot \begin{bmatrix} 1 \\ 1 \\ 1 \end{bmatrix} \right)

Congratulations

You Understand Inference of a Basic Neural Network

A Simple Network

b = -5

a = σ

b = 15

a = σ

b = -15

 

w=10

w=-10

w=10

w=-10

w=10

w=10

1

2

3

4

5

6

7

8

9

Parameters

HOW?

MAGIC PARAMETER NUMBERS!?

HOW?

MAGIC PARAMETER NUMBERS!?

Popular AI

TEXT GENERATION

  1. ChatGPT: The Leading AI model
  2. Gemini: Google's competetor to ChatGPT
  3. Llama 3: Best AI open source model from Meta
  4. Claude 3: GPT competitor by Anthropic
  5. Perplexity: ChatGPT for research
  6. MM1: Apple's Large Language Model
  7. Titan: Amazon's LLM - Comes in Express & Premiere
  8. Grok: Elon Musk's OpenAI competitor
  9. CoPilot: Microsoft's Coding Assistant
  10. CodeWhisperer: Amazon's CoPilot Competetor
  11. Tabnine: Copilot competitor company
  12. Jasper: AI copilot for marketing
  13. Mistral AI: Open source text gen models

Popular AI

Generative Images

  1. Midjourney: Easy AI Image Generator
  2. Dall-E: OpenAI Image Generator
  3. Adobe Firefly: AI tool from Adobe
  4. Stable Diffusion: Best Image Generation
  5. Getty iStock: "Commercially Safe" generation
  6. Synthesia: AI text to video
  7. Sora: OpenAI text to video
  8. Runway: AI text-to-video
  9. Pika: AI Video Generator

Popular AI

OTHER POPULAR AI

  1. ElevenLabs: AI text-to-speech & voice clone
  2. Suno: AI music generator
  3. Voice.ai: AI voice changer
  4. AIMastering.com: AI Audio Mastering
  5. Lalal.AI: Remove instrument or voices from music
  6. Text to Speech and Speech to Text (Too many!)

3. Demos

Let's Play!

  1. Frameworks
  2. Examples
  3. Explore

Math From Scratch?

NO!

Let's See Some AI Training

https://playground.tensorflow.org/

Let's Build a Model

https://teachablemachine.withgoogle.com/

WHY SHOULD YOU NOT USE THIS IN PRODUCTION?

4. Time to Code

Get Ready To Rock!

  1. Build It
  2. Chat About It

Let's Code!

https://github.com/tensorflow/tfjs-models

5. Custom Problems

Transfer Learning

  1. Demo Transfer
  2. Customize It

Let's Explore Data / Training

https://aisortinghat.com/

6. Let's LLM

Understand LLMs deeper

  1. Understand Generative AI
  2. Learn LLM Lingo

7. Questions & Answers

Let's Get Into It!

  1. Ethics & More?
  2. Guidance
  3. Early LUNCH!?

RENDER ATL - Workshops

By Gant Laborde

RENDER ATL - Workshops

  • 210

More from Gant Laborde