Matlab
Matlab toolbox
Deep learning toolbox
Neural network toolbox
Libraries
Functions
How to use
Python
Deep learning and Neural net libraries
Functions
How to use
Roll No. C039 Name: Jash Kahar
Class: B.Tech Intg sem 9 Batch: A2
Date of Experiment: 04/07/2020 Date of Submission: 11/07/2020
Grade:
MATLAB
MATLAB is a multi-paradigm numerical computing environment and proprietary programming
language developed by MathWorks. MATLAB allows matrix manipulations, plotting
of functions and data, implementation of algorithms, creation of user interfaces, and interfacing
with programs written in other languages.
Although MATLAB is intended primarily for numerical computing, an optional toolbox uses
the MuPAD symbolic engine allowing access to symbolic computing abilities. An additional
package, Simulink, adds graphical multi-domain simulation and model-based
design for dynamic and embedded systems.
MATLAB toolbox
The toolbox is a collection of functions built on the MATLAB technical computing
environment.
MATLAB Deep Learning & Neural Net Toolbox:
Deep Learning Toolbox™ provides a framework for designing and implementing
deep neural networks with algorithms, pretrained models, and apps.
You can use convolutional neural networks (ConvNets, CNNs) and long
short-term memory (LSTM) networks to perform classification and
regression on image, time-series, and text data.
You can build network architectures such as generative adversarial
networks (GANs) and Siamese networks using automatic differentiation,
custom training loops, and shared weights.
With the Deep Network Designer app, you can design, analyze, and train
networks graphically.
The Experiment Manager app helps you manage multiple deep learning
experiments, keep track of training parameters, analyze results, and
compare code from different experiments.
You can visualize layer activations and graphically monitor training
progress.
MATLAB Libraries & Functions
Python
Python is an interpreted, high-level, general-purpose programming language. Python's design
philosophy emphasizes code readability with its notable use of significant whitespace.
Its language constructs and object-oriented approach aim to help programmers write clear,
logical code for small and large-scale projects.
Python for Deep Learning and Neural nets
Python has been the go-to choice for Machine Learning and Artificial Intelligence developers for
a long time. Python offers some of the best flexibilities and features to developers that not only
increase their productivity but the quality of the code as well, not to mention the extensive
libraries helping ease the workload. Various features that put Python among the top programming
languages for Machine Learning, Deep Learning and Artificial Intelligence are listed below:
Free and open-source nature makes it community friendly and guarantees
improvements in the long run
Exhaustive libraries ensure there is a solution for every existing problem
Smooth implementation and integration make it accessible for people with the
varying skill level to adapt it
Increased productivity by reducing the time to code and debug
Can be used for Soft Computing, Natural Language Processing as well
Works seamlessly with C and C++ code module
Deep Learning and Neural nets for Python
1. Tensorflow
TensorFlow is one of the best libraries available for working with Machine Learning on
Python. Offered by Google, TensorFlow makes ML model building easy for beginners
and professionals alike. Using TensorFlow, you can create and train ML models on not
just computers but also mobile devices and servers by using TensorFlow Lite and
TensorFlow Serving that offers the same benefits but for mobile platforms and high-
performance servers.
a. Tensorflow Modules:
bitwise module: Operations for manipulating the binary representations of
integers.
data module: tf.data.Dataset API for input pipelines.
keras module: Implementation of the Keras API meant to be a high-level API for
TensorFlow
nn module: Wrappers for primitive Neural Net (NN) Operations.
optimizers module: Built-in optimizer classes.
test module: Testing.
train module: Support for training models.
b. Tensorflow Functions
Audio
i. decode_wav(...): Decode a 16-bit PCM WAV file to a float tensor.
ii. encode_wav(...): Encode audio data using the WAV file format.
Image
i. tf.image.resize: this function is used to resize images.
ii. tf.image.adjust_brightness: this is used to adjust the brightness of
the image.
iii. tf.image.crop_and_resize: this used to crop unnecessary data and
resize the image to the required size.
Math
i. Basic arithmetic operators and trigonometric functions.
ii. Special math functions (like: tf.math.igamma and tf.math.zeta)
iii. Complex number functions (like: tf.math.imag and tf.math.angle)
iv. Reductions and scans
(like: tf.math.reduce_mean and tf.math.cumsum)
v. Segment functions (like: tf.math.segment_sum)
2. Keras
Keras is one of the most popular and open-source neural network libraries for Python.
Initially designed by a Google engineer for ONEIROS, short for Open-Ended Neuro
Electronic Intelligent Robot Operating System, Keras was soon supported in
TensorFlow’s core library making it accessible on top of TensorFlow. Keras features
several of the building blocks and tools necessary for creating a neural network such as:
Neural layers
Activation and cost functions
Objectives
Batch normalization
Dropout
Pooling
Keras Functions
1. Model API
I. save_model function is used to save the model
II. load_model function is used to load a model into the program
2. Layer API
Layers are the basic building blocks of a keras neural network
I. Layer activation funtions like relu, sigmoid etc.
II. Layer weight constraints functions max, min etc.
3. Optimizers
It is one of the two commands required to compile a keras model
I. complie() is used to compile a model
II. fit() is used to fit a dataset to a model.
4. Metrics
it is used to judge the performance and the accuracy of the model.
