Sep 5, 2022Deploying custom model in AWS SagemakerIntroduction to AWS Sagemaker AWS Sagemaker is an service provided by AWS for creating, training and deploying machine learning models. It was launched in 2017 to enable developers easily create models by creating an ecosystem for all services needed for the entire machine learning lifecycle. Although Sagemaker is well equipped with many of the…Deployment3 min readDeployment3 min read
Jun 10, 2022A Gentle Introduction to LSTMIn the previous article, we learned about RNN’s and learnt that they have two problems that is vanishing gradients and exploding gradients. To overcome these problems, we have a state of the art method called LSTM- Long Short Term Memory. What are LSTM’s? Long Short-Term Memory (LSTM) networks are special RNNs, with different…Deep Learning3 min readDeep Learning3 min read
Published inMLearning.ai·Jun 9, 2022A Gentle Introduction to Recurrent Neural Networks(RNN)What are RNN’s and how do they work? Recurrent neural networks are a type of neural network used for sequential data. But before we dive deep into RNN’s lets understand what are neural networks. A Neural Network consists of different layers connected to each other, working on the structure and function of a human brain. …Data Science2 min readData Science2 min read
Jun 8, 2022Custom Classification using Amazon ComprehendWhat is AWS Comprehend? Comprehend is a AWS NLP service that allows users to gain insights from text data and build ML models. Go to AWS Comprehend- https://aws.amazon.com/comprehend/ Steps to perform classification using Comprehend: 1. Creating the classifier 2. Putting data into correct format. 3. Training 4. Make predictions (inference) Click on Custom ClassificationData Science2 min readData Science2 min read
Jun 7, 2022Optimization in Machine LearningThe goal of building machine learning models is to reduce the error to the minimum so that we can have the best generic model that can preform well for any data set. Learn better and better models, such that overall model error gets smaller and smaller … ideally, as small…Machine Learning3 min readMachine Learning3 min read
Jun 6, 2022A Complete Guide to Compact Prediction TreesIntroduction Compact Prediction Trees are a type of algorithm used to solve sequence problems.Recently, they have gained a lot of attention due to their fast raining and performance efficiencies. LSTM’s/RNN’s suffer from one major drawback that is long training time, plus re-training of unseen items. Enter … CPT!!! Compact Prediction Tree To understand CPT,we…Machine Learning3 min readMachine Learning3 min read
Jun 5, 2022A Gentle Introduction to Markov ChainsWhat are Markov chains? A Markov chain is a mathematical stochastic process defined as a collection of random variables, that transition from one state to another according to certain probabilistic rules. What is the Markov Property? These set of transition satisfies the Markov Property, which states that the probability of transitioning to any particular state is dependent solely on…Data Science3 min readData Science3 min read
Jun 4, 2022Word Embedding: Word2Vec — Skip-gram and CBOWWhat is Word Embedding? Word Embedding is a term used to describe numerical representation of text. We learnt some basic text vectoization techniques in the previous article such as Bag of Words, TF-IDF.. etc. Now let us look at some more advanced techniques for text representation. Creating a sparse representation using TF-IDF and other…Data Science3 min readData Science3 min read
Jun 2, 2022A Complete guide to K Nearest Neighbor (KNN) in Machine LearningK Nearest Neighbor or K-NN is a supervised learning algorithm that uses a non-parametric algorithm, which means it does not make any assumption on underlying data. …Data Science2 min readData Science2 min read
Jun 2, 2022Text Vectorization using Bag of Words and TF-IDFIn the previous article, we talked about how we can achieve basic text processing for text data. For any machine learning model, input has to be in numerical format. Hence, once we pre-process the text, the next step in to vectorize the text, i.e …Machine Learning3 min readMachine Learning3 min read