Skip to main content

Posts

Showing posts from January, 2020

Deep Learning: When To Stop Training Nueral Network?

Quick Recap An artificial neural network is a combination of artificial neurons which does some math and try to estimate a mathematical function. This estimation process is called training or fitting. Basic training mechanism The math involved in ANN is mostly MAC (Multiply-Accumulate) operations where the input is multiplied by weights and biases are added to the product. One of the activation functions is applied to the output and it is forwarded to the next layer and the same process continues until it reaches to the end layer. This process is called feed-forward. After the end layer calculation, the output computed by the network is compared with the actual output. The difference between actual output and estimated output is calculated using a function called loss function. Common loss functions these days are Mean Squared Error, Mean Absolute Error, Root MSE, Cross-Entropy etc. The error calculated using loss function is propagated backward throughout the neura...

10 Books That I Read In 2019

Photo by Kimberly Farmer on Unsplash Have you ever noticed what is the thing most common in the most successful people in the world? Reading. Warren Buffet, Bill Gates, Elon Musk, Imran Khan, Dan Pena, Jeff Bezos... all these leaders are good readers. They read several books a month. If you are already a reader that's well and good but if you are not, try to get started from now. Because a book is an extract of years of experience of its author. You can gain that giant amount of experience in a matter of hours. It is a good way to utilize free time too.  I personally love to read. There is no specific subject I read about but apart from my subject (computer science) I prefer to read about just personal development and history. However, I am trying to add more categories per year. There are arguments in favor of reading fiction but I would rather go for reading biographies. To avoid getting bored of reading, I do not read two consecutive books on the same subject....