About Abhineet Saxena

Abhineet Saxena is a Bachelors of Technology (B.Tech.) undergraduate student at Guru Gobind Singh Indraprastha University, New Delhi, India. He’s majoring in Computer Science and Engineering. His topics of interest include Machine Learning with special emphasis on Cluster Analysis and Neural Networks. He enjoys programming in Python, blogging and composing poetry in leisure time.

Tending To Infinity

What kind of thoughts does the word ‘infinity’ evoke in your mind? Do you visualize a never-ending expanse that stretches in all directions? Or maybe a straight line extending in both directions beyond visual perception. Some of us may even think of an astronomical figure and conceptualize infinity to lie much beyond this number itself. Yet, how does mathematics treat infinity? How do we logically/formally make sense of this idea and put it to great use to further enrich our understanding of this universe?

Let’s explore and demystify what this rather abstract construct really conveys to us through the language of mathematics. Continue reading

Convolutional Neural Networks (CNNs): An Illustrated Explanation

Artificial Neural Networks (ANNs) are used everyday for tackling a broad spectrum of prediction and classification problems, and for scaling up applications which would otherwise require intractable amounts of data. ML has been witnessing a “Neural Revolution”1 since the mid 2000s, as ANNs found application in tools and technologies such as search engines, automatic translation, or video classification. Though structurally diverse, Convolutional Neural Networks (CNNs) stand out for their ubiquity of use, expanding the ANN domain of applicability from feature vectors to variable-length inputs.

Continue reading

Neural Networks and Recent Accomplishments (and how to train your own NN: a Python based DIY)

Artificial Neural Networks (ANN) are computational models inspired from one of nature’s most splendid creations – the neuron. It seems our quest to make the machines smarter has converged onto the realization that we ought to code the ‘smartness’ into them, literally. What better way than to draw parallels from the source of our own intelligence, our brains?

Continue reading