PyCon Pune 2018

PyCon Pune

Building and Understanding a Neural Network from ground-up using NumPy

Submitted by Soumyo Dey (@ace139) on Sep 12, 2017

Technical level: Beginner Status: Submitted


Everyone is interested in Deep Learning these days and the implementation of a Neural Network has become easier using the libraries like Tensorflow, CNTK, Caffe2, PyTorch, Theano etc. It has become more easier to build using high-level wrapper libraries like Keras. This talk targets to explain what really happens in a neural network, how it runs with basic undestanding of concepts like Weights, Biases, Activation functions etc.


  1. What is Neural Network?
  2. Components of a Neural Network.
  3. Basics of NumPy
  4. Building NN from scratch
  5. Training and Testing


  1. Python3
  2. NumPy

Speaker bio

I am a recent graduate in Computer Science & Engineering and currently working in Convergytics, Bengaluru building data-driven business solutions. I am working with Python for more than 3 years now and take deep interest in the field of Data Science and Machine Learning.


  • Kushal Das (@kushaldas) Crew 2 years ago

    Thank you for submitting the talk to PyCon Pune. The talk selection team will contact you here in case of any queries. Meanwhile, please make sure that you provide a link to the presentation slides.

Login to leave a comment