Scribd
Upload
6 views

Unit V

The document introduces artificial neural networks (ANNs) as machine learning models inspired by biological neurons, emphasizing their evolution and significance in deep learning applications. It highlights the capabilities of ANNs in handling complex tasks such as image classification and speech recognition. Additionally, it discusses the use of TensorFlow's Data API for efficiently loading and preprocessing large datasets, including various data formats and encoding methods.

Uploaded by

Md.mohammed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
6 views

Unit V

The document introduces artificial neural networks (ANNs) as machine learning models inspired by biological neurons, emphasizing their evolution and significance in deep learning applications. It highlights the capabilities of ANNs in handling complex tasks such as image classification and speech recognition. Additionally, it discusses the use of TensorFlow's Data API for efficiently loading and preprocessing large datasets, including various data formats and encoding methods.

Uploaded by

Md.mohammed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

Unit V

Neural Networks and Deep Learning


Introduction to Artificial Neural Networks
with Keras
Birds inspired us to fly, burdock plants inspired
Velcro, and nature has inspired countless more
inventions. It seems only logical, then, to look at the
brain’s architecture for inspiration on how to build
an intelligent machine.
This is the logic that sparked artificial neural
networks (ANNs): an ANN is a Machine Learning
model inspired by the networks of biological neurons
found in our brains. However, although planes were
inspired by birds, they don’t have to flap their wings.
Similarly, ANNs have gradually become quite
different from their biological cousins.
ANNs are at the very core of Deep Learning.
They are versatile, powerful, and scalable,
making them ideal to tackle large and highly
complex Machine Learning tasks such as
classifying billions of images (e.g., Google
Images), powering speech recognition
services (e.g., Apple’s Siri), recommending
the best videos to watch to hundreds of
millions of users every day (e.g., YouTube), or
learning to beat the world champion at the
game of Go (DeepMind’s AlphaGo).
The Perceptron
The Multilayer Perceptron
Implementing MLPs with Keras
Installing TensorFlow 2
Loading and Preprocessing Data with TensorFlow.

So far we have used only datasets that fit in


memory, but Deep Learning systems are often
trained on very large datasets that will not fit in
RAM. Ingesting a large dataset and preprocessing
it efficiently can be tricky to implement with other
Deep Learning libraries, but TensorFlow makes it
easy thanks to the Data API: you just create a
dataset object, and tell it where to get the data
and how to transform it.
TensorFlow takes care of all the implementation
details, such as multithreading, queuing, batching,
and prefetching. Moreover, the Data API works
seamlessly with tf.keras!
Off the shelf, the Data API can read from text
files (such as CSV files), binary files with
fixed-size records, and binary files that use
TensorFlow’s TFRecord format, which
supports records of varying sizes. TFRecord
is a flexible and efficient binary format
usually containing protocol buffers (an open
source binary format).
The Data API also has support for reading
from SQL databases. Moreover, many open
source extensions are available to read from
all sorts of data sources, such as Google’s
BigQuery service.
Reading huge datasets efficiently is not the
only difficulty: the data also needs to be
preprocessed, usually normalized.
Moreover, it is not always composed strictly
of convenient numerical fields: there may be
text features, categorical features, and so on.
 These need to be encoded, for example using
one-hot encoding, bag-of-words encoding,

You might also like