This post contains my notes about the paper titled "An Empirical Exploration of Recurrent Network Architectures". You can read the paper here - http://proceedings.mlr.press/v37/jozefowicz15.pdf Abstract of the paper - The Recurrent Neural Network (RNN) is an extremely powerful sequence model that is often difficult to train. The Long Short-Term Memory (LSTM) is a specific RNN … Continue reading An Empirical Exploration of Recurrent Network Architectures: Paper Notes
This is one of the new things which I learnt this week. In this blog post we will talk about Template Specialization in C++. So I am really enjoying coding in Cpp and playing with the core internals. The power which comes which system level languages are amazing. You can actually go and see closely … Continue reading Template Specialization in C++
Hey guys, I am writing this blog post for beginners like me who want to understand CRDTs or distributed systems much. Quoting Wikipedia - "In distributed computing, a conflict-free replicated data type (CRDT) is a data structure which can be replicated across multiple computers in a network, where the replicas can be updated independently and concurrently without coordination between the replicas, and where it is always mathematically … Continue reading CRDTs: Introduction
In Reinforcement Learning, there is something known as Exploration vs Exploitation tradeoff. In this post I would be talking about the tradeoff and some personal dilemma as well. Follow this thread once - https://twitter.com/alienelf/status/1082949406977114112 I think if you are in self learning mode then you must have gone through this. So Let me explain a … Continue reading “Exploration vs Exploitation” Dilemma of autodidacts
With that start of 2019, I would like to point our attention to the danger we are posing to the world as AI community. I am not saying that the whole AI community is thoughtlessly progressing. No! The best part about our community is that we are thinking and debating openly about the steps we … Continue reading AI an embarrassment?
I know I know. It is really daunting to start learning deep learning today. I remember August-September of 2017 when I was starting to tiptoe in the waters of deep learning. I still remember reading my first paper and how formidable experience it was, specially for an autodidact programmer like me. I was so confused … Continue reading Which one should I choose as a beginner in Deep Learning pytorch or tensorflow?
I have been reading about Machine Learning extensively and discussing it with my friend who is doing M.Tech in IIT Kanpur. I tried to implement an LSTM in Tflearn which generates Indian City Names. In this blog post I am posting the output of this code. Wondering What LSTM is? I am posting definition from wiki- … Continue reading Generating Indian City Names
"If it looks like a duck and quacks like a duck, it's a duck". Didn't get anything? Worry not! I was as lost as you are right now after reading this statement about Duck Typing. So, it all started from a thought that how should I check whether an object is a list or not(in Python)? … Continue reading THE PYTHONIC DUCK
So this week at my work place I took baby steps to being a Data Scientist! I just peaked into distributed computing, data warehousing and data crunching(add more terms like these, to sound cool). Airflow and Hadoop ecosystem made me go "oh wow!". I built a very simple Twitter sentiment analysis big data solution using … Continue reading Airflow, Hadoop, Hue, Python and Twitter Sentiment Analysis