Resource Utilization as a metric for Machine Learning
Name: Akshay Bahadur
Symantec, Pune, India
The advent of machine learning along with its integration with big data has enabled users to
efficiently to develop solutions for innumerable use cases. A machine learning model consists
of an algorithm which draws some meaningful correlation between the data without being
tightly coupled to a specific set of rules. It's crucial to explain the subtle nuances of the
network along with the use-case we are trying to solve. With the advent of technology,
the quantity of data has increased which in turn has increased the need for resources to
process the data while building a model. The main question, however, is to discuss the need
to develop lightweight models keeping the performance of the system intact.
To connect the dots, we will talk about the development of these applications specifically
aimed to provide equally accurate results without using much of the resources. This is
achieved by using image processing techniques along with optimizing the network
architecture.
Outline
The presentation will have code excerpts for the preprocessing and computer vision part for
filtering out the unwanted background from the data. Each excerpt will be followed by a
demo of how the changes work in real-time.
For instance, I will be taking up a research paper by NVIDIA on behavioral cloning for self-
driving cars. We can reduce the number of trainable parameters of the model proposed in the
paper by 50% if we use an optimized CNN model, thus saving on training and prediction
time ( the total trainable parameters , as per the model described in the research paper, are
132,501. However, with my implementation, we only need to train 80,213 parameters).
First, we will start with formulating and addressing a strong problem statement followed by a
thorough literature review. Once these things are taken care of, we will discuss the data
gathering part, followed by the algorithm evaluation and future scope.
While giving each of the demos, I would be talking about the models and algorithms used.
Why is the literature review the most important phase of your project? How contributing to
the community helps you ultimately.
Demonstrations
● MNIST [10 mins]
● Autopilot (NVIDIA) [15 mins]
● Emojinator [15 mins]
● Malaria Detection [10 mins]
● Quick, Draw (Google) [15 mins]
Techniques for minimization of CPU resources
● Normalization of data (When using on MNIST dataset, the unnormalized data takes
371us/step (accuracy - 22%), however, the normalized data takes 323us/step(accuracy
-73%)) [20 mins]
● Stripping channels from the images. Instead of all the 3 color channels, can use only 1
or use them separately to train the model. [10 mins]
● Hyperparamter tuning and how to affects the epoch training rate
● Rescaling/augmentation of the data. [10 mins]
● Designing filters to filter out the object/region of interest and removing the excessive
background noise. [20 mins]
● Using fit_generator capability of tensorflow. Instead of loading the entire dataset at
once which might crash the RAM. We can use multiprocessing in loading data batch-
wise at runtime. [20 mins]
Target audience and outcome : This tutorial is aimed at machine learning practitioners who
have relevant experience in this field with basic understanding of neural networks and image
processing would be highly appreciated. By the end of the session, the audience will have a
clearer understanding of building vision based optimized models that can be run on low
resources. In a developing country like India, the crux of the problem lies with the
requirement of heavy resources for performing computation. With the help of this tutorial, I
want to share my insight on developing learning models frugally and efficiently.
Bio
Akshay Bahadur’s interest towards computer science sparked when he was working on a
women's safety application aimed towards the women welfare in India and since then he has
been incessantly working on improving my skills. He has made successful prototypes like
autonomous car, alphabet recognition, cancer classification, gesture recognition using
learning models. His ambition is to make valuable contribution towards ML community and
leave a message of perseverance and tenacity. Currently, he is working as a software engineer
at Symantec, India. He’s is one out of 8 Google Developer Expert (Machine Learning) from
India along with being one of 150 members worldwide for Intel Software Innovator program.
His recent contribution on developing an Indian Sign Language Recognition(ISLAR) has
been appreciated worldwide.
Presenting author details
Full name: Akshay Bahadur
Portfolio: https://www.akshaybahadur.com/
Linked In account: https://www.linkedin.com/in/akshaybahadur21
Relevant experience of author
GDE Summit, California 2019
Link : https://youtu.be/QU-SIQ_qUeQ
Google DevFest Kokata 2019
Link : https://www.youtube.com/watch?v=3AFAwWuICDE
Open Data Science Conference (ODSC), India 2019
https://www.youtube.com/watch?v=cbaKSVSRTas
Indian Institute of Science, 2019
https://www.youtube.com/watch?v=QixqQgQiMRU
Open Data Science Conference (ODSC), Boston 2019
Link : https://learnai.odsc.com/courses/deepvision-exploiting-computer-vision-techniques-to-
minimize-cpu-utilization
Open Data Science Conference (ODSC), India 2018:
Demo : https://www.youtube.com/watch?v=KKSpX7YrY3A
DeepCogntion Workshop:
Link : https://www.youtube.com/watch?v=KakD2UnEpZM
Institute of Analytics:
Part 1 : https://www.youtube.com/watch?v=wVx1tF3QDHU
Part 2 : https://www.youtube.com/watch?v=7y9AwiFYnjQ
Microsoft Advanced Analytics User group:
Link : https://www.youtube.com/watch?v=A2baXaZ8pnQ
Presentation requirements : Projector, internet connection, HDMI connector, presentation
pointers
300 Word Abstract:
The advent of machine learning has enabled users to efficiently to develop solutions for
innumerable use cases which requires heavy resource-centric systems. However, it is
important to discuss the need to develop lightweight models keeping the performance of the
system intact.
