TensorFlow from the ground up (ML Tech Talks)

preview_player
Показать описание
In the next talk in our series, Wolff Dobson will discuss 6 easy pieces on what you need to know for TensorFlow from the ground up (tensors, variables, and gradients without using high level APIs). This talk is designed for those that know the basics of Machine Learning but need an overview on the fundamentals of TensorFlow.

Chapters:
0:00 - Intro and outline
2:12 - Tensors
6:08 - Variables
9:19 - Gradient tape
13:57 - Modules
17:43 - Training loops
28:53 - Conclusion

Resources:

  1. TensorFlow
  2. GDS: Yes
  3. tensorflow from the ground up
  4. tf from the ground up
  5. tensorflow basics
  6. tf basics
Рекомендации по теме
TensorFlow from the 0:30:15

TensorFlow from the ground up (ML Tech Talks)

Ditch Python! Swift 0:11:58

Ditch Python! Swift For TensorFlow AND FastAI: Part 1 | Jeremy Howard

Building a neural 0:31:28

Building a neural network FROM SCRATCH (no Tensorflow/Pytorch, just numpy & math)

TensorFlow 2.0 Complete 6:52:08

TensorFlow 2.0 Complete Course - Python Neural Networks for Beginners Tutorial

Graph Neural Networks 0:14:28

Graph Neural Networks - a perspective from the ground up

But what is 0:18:40

But what is a neural network? | Chapter 1, Deep learning

TensorFlow 2.0 - 0:10:43

TensorFlow 2.0 - A Coding Tutorial

1.0 Deep Learning 0:01:56

1.0 Deep Learning using Tensorflow - Introduction

Vulkan & OpenGL 0:33:40

Vulkan & OpenGL AI Game Engine from scratch || Starting over Day 1

Coding a Neural 0:11:59

Coding a Neural Network From Ground Up with Python

MLIR Open Meeting 0:53:46

MLIR Open Meeting 2019-08-01: TensorFlow Graph Representation in MLIR

Building LLMs from 2:45:10

Building LLMs from the Ground Up: A 3-hour Coding Workshop

Build and Train 0:26:54

Build and Train Your First TensorFlow Graph

State-of-the-art Machine Learning 0:03:41

State-of-the-art Machine Learning research with Google tools | Keynote

Machine Learning with 0:41:00

Machine Learning with TensorFlow • Robert Saxby & Rokesh Jankie • GOTO 2017

Siamak Ashrafi - 0:46:35

Siamak Ashrafi - Swifty TensorFlow

Machine Learning With 1:15:06

Machine Learning With Python And TensorFlow

Learning TensorFlow 0:40:42

Learning TensorFlow

3.8 Deep Learning 0:01:34

3.8 Deep Learning using Tensorflow - make moons without hidden layers

TensorFlow in production: 0:36:49

TensorFlow in production: TF Extended, TF Hub, and TF Serving (Google I/O '18)

Machine Learning in 1:12:53

Machine Learning in Python: Convolutional Networks for Semantic Segmentation in TensorFlow and Keras

3.9 Deep Learning 0:03:31

3.9 Deep Learning using Tensorflow - make moons with hidden layers

2.5 Deep Learning 0:02:57

2.5 Deep Learning using Tensorflow - Automatic Differentiation

Introduction to Neural 2:05:11

Introduction to Neural Network Programming with Tensorflow

Комментарии
Автор

Damn, this was a fantastic talk. I've been using Tensorflow for 3 years now and am a certified tensorflow developer and I feel like I learned so much about the lower-level stuff. Definitely not a talk for beginners to hop into but a fantastic resource for intermediate tf users who want to fill in the gaps. Great work and really good presentation!

timogden
Автор

Wow, this is an outstanding overview of TensorFlow & all it’s moving parts! Thank you

mrdbourke
Автор

Excellent talk! I would say you should watch this once you've played around a bit in TF. Then it would be like looking back from a vantage point at a mountain road with lots of switch backs. Gives a sense of clarity.

rajeshv
Автор

Imagine having the ability to control speed and direction of wind fields to loft marbles to have them fall at the right time, and a game controller where you can deform to the shapes of the buttons (PCA) to catch all the marbles. and all the if statements that get triggered when a button gets pressed, throwing away the ones that give you the lower score o.o

WhenThoughtsConnect