Implementing Neural Networks using TensorFlow
TensorFlow is an open source software library for numerical computation using dataflow graphs. Nodes in the graph represents mathematical operations, while graph edges represent multi-dimensional data arrays (aka tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.
->Define Neural Network architecture to be compiled
->Transfer data to your model
->The model then gets trained incrementally
->Display the accuracy for a specific number of timesteps
->After training save the model for future use
->Test the model on a new data and check how it performs
Kapil Bakshi is a very passionate techie with an aim to embrace technology, imbibe every bit of it, transcend all the barriers and turn ideas into reality. His experience spans across edtech, fintech and logistics sectors where he has developed things from scratch taking them to a level where they have scaled drastically and have become a brand in their respective domains.
He is currently working at BlackBuck which is redefining the logistics landscape of India, making it reliable and efficient. Kapil is playing an important role there to improve quality of all apps, doing optimisations and helping the company scale to go much beyond.
He is a full stack developer and many times single-handedly built complex features which have proven to be very beneficial for business.
His areas of interest include testing, architectural best practices and security.