Guidelines for Proposal Submission #

Following are the guidelines for proposal submission

Please mention type of Proposal as given below in the Title of the Proposal.
The proposal should have an objective with clear expectation for the audience.
The Proposal description should be short and to the point.
The proposal should have proper prerequisites like environment setup, library version.
No proposal will be selected without a link to appropriate session content like presentation, pdf, code snippets etc.
Proposal content should adhere to code of conduct.
Proposal content links can be updated later.
Proposal content shouldn’t have a company name throughout the content. Mention of the employer is allowed only at the beginning of the content (presentation/pdf).
Background image/wallpaper shouldn’t contain company name/logos.
For any questions, please write to contact@hydpy.org.

Proposal Types #

We have three kind of Proposals - General Talks, Lightning Talks and Workshops. Please mention the Proposal type in the Title of the Proposal. Give a Title like Proposal Type : Proposal Title

General Talks #

These are the traditional talk sessions scheduled during the first day of conference. They will be conducted on Day 2 of Conference, Sunday, 8th Oct. The length of these tracks are 45 minutes.

Lightning Talks #

These are short length talks that will be conducted on Day 2 of Conference, Sunday, 8th Oct. The time limit is 5 minutes. But we can extend it depending on number of talks submitted.

Workshops #

As with the talks, we are looking for Workshops that can grow this community at any level. We aim for Workshops that will advance Python, advance this community, and shape the future. Each session runs for 6 full hours plus a break for lunch. There will be 2 workshops going parallely on Day 1 of Conference, Saturday, 7th Oct in the same venue that hosts the main conference. Workshop I is aimed for Begineers while Workshop II is a Advaced Session aimed for Professionals.

Themes and Topics #

These will be the themes and topics

Core Python and Python 3 features
Concurrent and Asynchronous programming in Python
Data Science and Analysis
Web Development
Python and IOT
Functional Programming
Artificial Intelligence
Continuous integration and Deployment
Testing
Scientific Computing
Cloud computing with Python

Important Dates #

31st August, 2017 : Deadline for Proposal Submission
16th September, 2017 : Talk selection and announcement

Hosted by

pyconfhyd

Submit Proposals for PyConf Hyderabad more

All submissions

Previous Next

General Talk: Neural Networks from zero (using only numpy) to practical projects (using scikit-learn and TensorFlow)

Submitted Aug 28, 2017

Technical level: Beginner

Artificial Neural Networks (ANN henceforth) are being used increasingly ever in recent years, and some consider it as a master key for almost all machine learning problems. There are many toolkits and libraries (tools henceforth) available, but I myself have never been comfortable with such tools until I understand (at least partially) what’s going on under the hood. I’m in no way saying that these tools are poorly documented or have a difficult learning curve, it’s just the way I tend to learn. Assuming that I am not alone in this regard, I would like to help others in their quest to understand and master ANN by giving my bit.

Talk level is between beginner to somewhat intermediate.

Outline #

The talk will start with explaining (only a little about) ideas behind ANNs very very briefly, after which some basic & trivial examples will follow.
The talk will mainly focus on two parts:
Firstly, to show how to implement an ANN which practically ‘does something’, using only python and numpy (for functionalities like np.dot, np.reshape which are not directly part of ANN).
Second part will consist of peeking (a little) inside tools like scikit-learn & TensorFlow and see how real world (or at least practical, atm) applications can be/are developed with them.
Numerous interesting and notable projects using these (or any other like caffe) will be mentioned in the end to show capabilities of ANNs.

Q & A if any!

Bonus (if time & interests permit):
Using PyCUDA for ANN computations
NLTK.
Caffe.

Requirements #

python understanding and programming experience.
Beneficial but not strictly required knowledge:
numpy
Machine learning approach towards problem solving.

Speaker bio #

Another software developer doing a regular job in IT. I’ve been working with Google and have been using python as a major pillar in my tech-stack for more than 7 years.