Download as pdf or txt
Download as pdf or txt
You are on page 1of 13

Deep Learning

with TensorFlow
By: Andrei Neagoie, Daniel Bourke
Objective
Introduction to Machine Learning and Deep Learning
Fundamentals of Tensorflow
What is Machine Learning?
Machine Learning is turning things (Data) into numbers and finding
patterns in those numbers.
The most popular technique of predicting the future or classifying
information is to help people make necessary decisions.
How does Machine Learning Work?
What is Deep Learning?
Deep learning is the evolution of machine learning and Artificial Intelligence

neural networks, training to find patterns hidden in


Machine Learning
large unstructured data sets such as images, videos, or
audio.
Deep Learning
Machine Learning vs Deep Learning
ML algorithms learn from structured datasets while DL algorithms are
based on highly complex neural networks with unstructured data.
ML corporates with small datasets while DL has to be trained on a large
dataset.
Random Forest, Naive Bayes, Nearest Neighbor, and more; Nural Networks,
CNN, RNN, Transformer, and more;
Why use Deep Learning?
Problems with long lists of rules.
Continually changing environment.
Discovering insights with large amounts of data.
What are Neural Network?
Anatomy of a Neural Network

Output Layer
Input Layer

Hidden Layers
Applications of Deep Learning
Video Recomendation
Natural Language Processing (NLP)
Speech Recognition
Computer Vision an so on
Why use TensorFlow?
Open- source
Easy model building
End-to-end platform for machine learning
Able to run on a GPU/TPU
Able to access many pre-built deep learning models
What is a Tensor?
A n-dimensional array of numbers
Fundamentals
Import tensorflow
tf.constat
tf.variable
tf.random
Shuffling the order
Other way to make tensors
NumPy arrays into tensors
Getting info from tensors

You might also like