Visualizing Deep Learning

Visualizing Deep Learning

vcubingx provides a visual introduction to the structure of an artificial neural network.

The Neural Network, A Visual Introduction | Visualizing Deep Learning, Chapter 1

  • 0:00 Intro
  • 1:55 One input Perceptron
  • 3:30 Two input Perceptron
  • 4:40 Three input Perceptron
  • 5:17 Activation Functions
  • 6:58 Neural Network
  • 9:45 Visualizing 2-2-2 Network
  • 10:59 Visualizing 2-3-2 Network
  • 12:33 Classification
  • 13:05 Outro

College Algebra Free and Full 6 Hour+ Course

College Algebra Free and Full 6 Hour+ Course

Learn Algebra in this full college course. Algebraic concepts are often used in programming. 

This course was created by Dr. Linda Green, a lecturer at the University of North Carolina at Chapel Hill. Check out her YouTube channel: https://www.youtube.com/channel/UCkyLJh6hQS1TlhUZxOMjTFw  

Chapters:

  • (0:00:00) Exponent Rules
  • (0:10:14) Simplifying using Exponent Rules
  • (0:21:18) Simplifying Radicals
  • (0:31:46) Factoring
  • (0:45:08) Factoring – Additional Examples
  • (0:55:37) Rational Expressions
  • (1:05:00) Solving Quadratic Equations
  • (1:15:22) Rational Equations
  • (1:25:31) Solving Radical Equations
  • (1:37:01) Absolute Value Equations
  • (1:42:23) Interval Notation
  • (1:49:35) Absolute Value Inequalities
  • (1:56:55) Compound Linear Inequalities
  • (2:05:59) Polynomial and Rational Inequalities
  • (2:16:20) Distance Formula
  • (2:20:59) Midpoint Formula
  • (2:23:30) Circles: Graphs and Equations
  • (2:33:06) Lines: Graphs and Equations
  • (2:41:35) Parallel and Perpendicular Lines
  • (2:49:05) Functions
  • (3:00:53) Toolkit Functions
  • (3:08:00) Transformations of Functions
  • (3:20:29) Introduction to Quadratic Functions
  • (3:23:54) Graphing Quadratic Functions
  • (3:33:02) Standard Form and Vertex Form for Quadratic Functions
  • (3:37:18) Justification of the Vertex Formula
  • (3:41:11) Polynomials
  • (3:49:06) Exponential Functions
  • (3:56:53) Exponential Function Applications
  • (4:08:38) Exponential Functions Interpretations
  • (4:18:17) Compound Interest
  • (4:29:33) Logarithms: Introduction
  • (4:38:15) Log Functions and Their Graphs
  • (4:48:59) Combining Logs and Exponents
  • (4:53:38) Log Rules
  • (5:02:10) Solving Exponential Equations Using Logs
  • (5:10:20) Solving Log Equations
  • (5:19:27) Doubling Time and Half Life
  • (5:35:34) Systems of Linear Equations
  • (5:47:36) Distance, Rate, and Time Problems
  • (5:53:20) Mixture Problems
  • (5:59:48) Rational Functions and Graphs
  • (6:13:13) Combining Functions
  • (6:17:10) Composition of Functions
  • (6:29:32) Inverse Functions

GPT-3: Language Models are Few-Shot Learners

GPT-3: Language Models are Few-Shot Learners

How far can you go with ONLY language modeling?

Can a large enough language model perform NLP task out of the box?

OpenAI take on these and other questions by training a transformer that is an order of magnitude larger than anything that has ever been built before and the results are astounding.

Yannic Kilcher explores.

Paper

Time index:

  • 0:00 – Intro & Overview
  • 1:20 – Language Models
  • 2:45 – Language Modeling Datasets
  • 3:20 – Model Size
  • 5:35 – Transformer Models
  • 7:25 – Fine Tuning
  • 10:15 – In-Context Learning
  • 17:15 – Start of Experimental Results
  • 19:10 – Question Answering
  • 23:10 – What I think is happening
  • 28:50 – Translation
  • 31:30 – Winograd Schemes
  • 33:00 – Commonsense Reasoning
  • 37:00 – Reading Comprehension
  • 37:30 – SuperGLUE
  • 40:40 – NLI
  • 41:40 – Arithmetic Expressions
  • 48:30 – Word Unscrambling
  • 50:30 – SAT Analogies
  • 52:10 – News Article Generation
  • 58:10 – Made-up Words
  • 1:01:10 – Training Set Contamination
  • 1:03:10 – Task Exampleshttps://arxiv.org/abs/2005.14165
    https://github.com/openai/gpt-3