Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
ISI Programming Course - 07 - Tensorflow
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Jungwon Seo
October 29, 2018
0
99
ISI Programming Course - 07 - Tensorflow
Jungwon Seo
October 29, 2018
Tweet
Share
More Decks by Jungwon Seo
See All by Jungwon Seo
MLOps Research
codethief
0
42
ISI Programming Course - 06 - Scikit Learn
codethief
0
37
ISI Programming Course - 05 - Python Data Science Libraries
codethief
0
70
ISI Programming Course - 04 - Python
codethief
0
140
ISI Programming Course - 03 - Javascript
codethief
0
120
ISI Programming Course - 02 - CSS
codethief
0
83
ISI Programming Course - 01 - HTML
codethief
0
150
Let's study web-development
codethief
0
78
Featured
See All Featured
Designing for Performance
lara
610
70k
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.1k
The Power of CSS Pseudo Elements
geoffreycrofte
80
6.2k
Dominate Local Search Results - an insider guide to GBP, reviews, and Local SEO
greggifford
PRO
0
77
SEO Brein meetup: CTRL+C is not how to scale international SEO
lindahogenes
0
2.3k
How GitHub (no longer) Works
holman
316
140k
YesSQL, Process and Tooling at Scale
rocio
174
15k
How to audit for AI Accessibility on your Front & Back End
davetheseo
0
180
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
55
3.2k
Code Review Best Practice
trishagee
74
20k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Designing Experiences People Love
moore
144
24k
Transcript
Jungwon Seo | University of Stavanger ISI Programming Class Tensorflow
Tensorflow • Originally developed by Google. • Mainly for Deep
Neural Network.
Why do we need to use this?
Flexibility, Scalability, Portability
Again! Neural Network
Neuron
Activation Function
Backpropagation
Gradient descent
Minimum Error
Learning Rate
1. Convolutional Neural Network • Good fit with image recognition.
2. Recurrent Neural Network • Good fit with text and
audio data.
Deep learning can’t solve the problem that you don’t know
how to solve.