Neural Networks – Feedforward Math

In this post, we will do the math on our dummy dataset and calculate the feedforward steps by hand. We will take the parameters of our first instance, i.e. first house, as the input vector and arbitrarily chosen random weights. Our dummy dataset was as follows: INSTANCE SQFT NUM_BED NUM_BATH house 1 1500 2 2 house 2 1700 3 2 house 3 1750 3 3 dummy housing data Let’s recall how the feature vector and weights are multiplied to get the input to hidden layer which will be the values of our hidden nodes. Let’s see what goes into the … Continue reading Neural Networks – Feedforward Math

Neural Networks – Feedforward process

What happens when the input goes into the model? It makes its way through the network architecture to the output layer. This process is called Feed-forward process and results in the prediction or classification of the problem we’re building the model for. We will begin with a brief overview and then peel the layers as we proceed. Things to know: Vectors Matrices Matrix Multiplication /Dot Product Components of a Feed-forward process: Input Layer Weight matrices Activation functions Bias The Process- A brief overview: Your data goes into the model in the form of an input vector. This vector is then … Continue reading Neural Networks – Feedforward process

3-year milestone: Reflections on the odyssey

August 7th 2017, the day I landed in San Francisco, California. I remember being so scared that I considered taking the next flight back without even getting out of the airport. It’s not that I didn’t want to be there, I just never expected to be and the very manifestation of something that I was too scared to even dream, petrified me. “What if I fail?”, “I’m never going to make it past the first semester”, “It’s too late (I’m too old) to start a career”- these are just some of the things I told myself. I was gearing up … Continue reading 3-year milestone: Reflections on the odyssey

Introduction – Hello World!!

Hi there! This blog probably has the most cliche title in the computer science world, but the shoe fits, so why not. This is my very first blog so it is befitting that I introduce myself and outline what I plan to do and write about. My name is Shahzina Khan and I am a data analyst, learning my way into becoming a data scientist. My short-term goal is to specialize in Natural Language Processing and my long-term goal is to research Reinforcement Learning in NLP and find the key to the answers of the universe, or something like that. … Continue reading Introduction – Hello World!!