Published in The Startup·PinnedDynamic Notebooks for Versatile AIAnd why it might just be beneficial to generalize models — Dynamic Notebooks for training identical models for every use case, to make Artificial Intelligence easier and more efficient. Growth of Versatility in AI From the earliest days of Artificial Intelligence, there has been notable importance given to the adaptability of the models, starting from Alan Turing himself who, in his 1936 paper titled On Computable…Data Science4 min read
Published in Towards Data Science·Aug 7, 2021Write better match statements in RustUsing closures to write cleaner match statements — If you’ve programmed in Rust, you’ve surely used the match statement. It is the preferred way for decision-making in Rust, along with if-let statements. However, many beginners may end up having redundancy while using match statements, with repetitive patterns leading to less readability and bad code. Situation To understand how to…Rustlang4 min read
Published in Towards Data Science·Jun 12, 2021Going beyond BinaryUnderstanding the world of Quantum Computing ⚛ — What is Quantum Computing? Let’s consider a ‘classical’ computer, one where every bit is in one of two states, 0 or 1 , often considered to be on or off. A quantum bit, better known as a qubit, is equivalent to Quantum computers. …Quantum6 min read
Jan 4, 2021MediaPipe jS: TFjS on SteroidsGoogle’s latest browser-based ML venture — If you’re in the Machine Learning field, you’ve surely heard or worked on TensorFlow and maybe its JavaScript variant, TensorFlow.jS. If not, here’s a quick tutorial to get you started. Anyways, the basic concept of these libraries is to allow the functioning of Machine Learning models in the browser. Wait, aren’t browsers slow? Glad…Tensor Flow4 min read
Published in Towards Data Science·Nov 3, 2020Definitive Guide of Activations in Machine LearningList of all Activation Functions you’d ever need — For any Machine Learning model, one of the most critical decisions is the choice of which activation to use. Let’s go through all the activation functions you’d ever wanna know about. The order of this list is in the Increasing Usage. Index Here’s a quick list if you wanna jump right…Data Science7 min read
Published in Towards Data Science·Oct 30, 2020Create Efficient Data PipelinesUse TensorFlow Datasets and tf.data to easily get your Raw Data into your model — Let’s get these clear, existing Datasets aren’t enough While most Machine Learning programmers start with common open-source datasets like MNIST or CIFAR-10, and that’s all well and good, but to expand your horizon, and solve problems, you need to go beyond these and get your own data. While the collection of data may or may not be too…Tensor Flow6 min read
Published in Towards Data Science·May 2, 2020How to deploy your ML models into the browserAnd how to do so effectively. — When I was a beginner in AI and ML, I often had questions like why am I learning this? And could I even make a difference before landing at a job? These questions came up because I knew how to train models, but not how to deploy them. …Deep Learning5 min read
Published in Towards Data Science·Apr 22, 2020How to start a Machine Learning blog in a monthHow I did it, and you can do it too! — I am Dweep, a deep learning enthusiast. I have finished lots of ML and AI courses, and I felt it was time for me to give back to the community. So I started a blog on Blogger named LightSpeedAC, to share my knowledge to the thousands willing to get into…Deep Learning5 min read
