Category Archives: Machine Learning
50+ Machine learning & Deep learning Youtube Courses
In this post, you get an access to curated list of 50+ Youtube courses on machine learning, deep learning, NLP, optimization, computer vision, statistical learning etc. You may want to bookmark this page for quick reference and access to these courses. This page will be updated from time-to-time. Enjoy learning! Course title Course type URL MIT 6.S192: Deep Learning for Art, Aesthetics, and Creativity Deep learning https://www.youtube.com/playlist?list=PLCpMvp7ftsnIbNwRnQJbDNRqO6qiN3EyH AutoML – Automated Machine Learning AutoML https://ki-campus.org/courses/automl-luh2021 Probabilistic Machine Learning Machine learning https://www.youtube.com/playlist?list=PL05umP7R6ij1tHaOFY96m5uX3J21a6yNd Geometric Deep Learning Geometric deep learning https://www.youtube.com/playlist?list=PLn2-dEmQeTfQ8YVuHBOvAhUlnIPYxkeu3 CS224W: Machine Learning with Graphs Machine learning https://www.youtube.com/playlist?list=PLoROMvodv4rPLKxIpqhjhPgdQy7imNkDn MIT 6.S897 Machine Learning for Healthcare Machine learning https://www.youtube.com/playlist?list=PLUl4u3cNGP60B0PQXVQyGNdCyCTDU1Q5j Deep Learning and Combinatorial Optimization Deep …
MOSAIKS for creating Climate Change Models
In this post, you will learn about the framework, MOSAIKS (Multi-Task Observation using Satellite Imagery & Kitchen Sinks) which can be used to create machine learning linear regression models for climate change. Here is the list of few prediction use cases which has already been tested with MOSAIKS and found to have high model performance: Forest cover Elevation Population density Nighttime lights Income Road length Housing price Crop yields Poverty mapping What is MOSAIKS? MOSAIKS provides a set of features created from Satellite imagery dataset. We are talking about 90TB of data gathered per day from 700+ satellites. These features can be combined with machine learning algorithms to address global …
Machine Learning – Feature Selection vs Feature Extraction
In this post, you will learn about the difference between feature extraction and feature selection concepts and techniques. Both feature selection and feature extraction are used for dimensionality reduction which is key to reducing model complexity and overfitting. The dimensionality reduction is one of the most important aspects of training machine learning models. As a data scientist, you must get a good understanding of dimensionality reduction techniques such as feature extraction and feature selection. In this post, the following topics will be covered: Feature selection concepts and techniques Feature extraction concepts and techniques When to use feature selection and feature extraction Feature Selection Concepts & Techniques Simply speaking, feature selection …
Machine Learning for predicting Ice Shelves Vulnerability
In this post, you will learn about usage of machine learning for predicting ice shelves vulnerability. Before getting into the details, lets understand what is ice shelves vulnerability and how it is impacting global warming / climate change. What are ice shelves? Ice shelves are permanent floating sheets of ice that connect to a landmass. Most of the world’s ice shelves hug the coast of Antarctica. Ice from enormous ice sheets slowly oozes into the sea through glaciers and ice streams. If the ocean is cold enough, that newly arrived ice doesn’t melt right away. Instead it may float on the surface and grow larger as glacial ice behind it continues to flow into the …
Python – Text Classification using Bag-of-words Model
In this post, you will learn about the concepts of bag-of-words (BoW) model and how to train a text classification model using Python Sklearn. Some of the most common text classification problems includes sentiment analysis, spam filtering etc. In these problems, one can apply bag-of-words technique to train machine learning models for text classification. It will be good to understand the concepts of bag-or-words model while beginning on learning advanced NLP techniques for text classification in machine learning. The following topics will be covered in this post: What is a bag-of-words model? How to fit a bag-of-words model using Python Sklearn? How to fit a text classification model using bag-of-words technique? …
Support Vector Machine (SVM) Interview Questions – Set 1
This quiz consists of questions and answers on Support Vector Machine (SVM). This is a practice test (objective questions and answers) that can be useful when preparing for interviews. The questions in this and upcoming practice tests could prove to be useful, primarily, for data scientists or machine learning interns/freshers/beginners. The questions are focused on some of the following areas: Introduction to SVM Types of SVM such as maximum-margin classifier, soft-margin classifier, support vector machine Some of the key SVM concepts to understand while preparing for the machine learning interviews are following: SVM concepts and objective functions SVM kernel functions, tricks Concepts of C and Gamma value Scikit learn libraries for …
Free Online Books – Machine Learning with Python
This post lists down free online books for machine learning with Python. These books covers topiccs related to machine learning, deep learning, and NLP. This post will be updated from time to time as I discover more books. Here are the titles of these books: Python data science handbook Building machine learning systems with Python Deep learning with Python Natural language processing with Python Think Bayes Scikit-learn tutorial – statistical learning for scientific data processing Python Data Science Handbook Covers topics such as some of the following: Introduction to Numpy Data manipulation with Pandas Visualization with Matplotlib Machine learning topics (Linear regression, SVM, random forest, principal component analysis, K-means clustering, Gaussian …
42 Free Online Books on Machine Learning & Data Science
This post represents a comprehensive list of 42 free books on machine learning which are available online for self-paced learning. This would be very helpful for data scientists starting to learn or gain expertise in the field of machine learning / deep learning. Please feel free to comment/suggest if I missed to mention one or more important books that you like and would like to share. Also, sorry for the typos. Following are the key areas under which books are categorized: Pattern Recognition & Machine Learning Probability & Statistics Neural Networks & Deep Learning List of 42 Online Free eBooks on Machine Learning Following is a list of 35 FREE online …
Different types of Machine Learning Problems
This post describes the most popular types of machine learning problems using multiple different images/pictures. The following represent various different types of machine learning problems: Supervised learning Unsupervised learning Reinforcement learning Transfer learning Imitation learning Meta-learning In this post, the image shows supervised, unsupervised, and reinforcement learning. You may want to check the explanation on this Youtube lecture video. Unsupervised Learning Problems In unsupervised learning problems, the learning algorithm learns about the structure of data from the given data set and generates fakes or insights. In the above diagram, you may see that what is given is the unlabeled dataset X. The unsupervised learning algorithm learns the structure of data …
Top 10+ Youtube AI / Machine Learning Courses
In this post, you get access to top Youtube free AI/machine learning courses. The courses are suitable for data scientists at all levels and cover the following areas of machine learning: Machine learning Deep learning Natural language processing (NLP) Reinforcement learning Here are the details of the free machine learning / deep learning Youtube courses. S.No Title Description Type 1 CS229: Machine Learning (Stanford) Machine learning lectures by Andrew NG; In case you are a beginner, these lectures are highly recommended Machine learning 2 Applied machine learning (Cornell Tech CS 5787) Covers all of the most important ML algorithms and how to apply them in practice. Includes 3 full lectures …
Difference between Online & Batch Learning
In this post, you will learn about the concepts and differences between online and batch learning in relation to how machine learning models in production learn incrementally from the stream of incoming data. It is one of the most important aspects of designing machine learning systems. Data science architects would require to get a good understanding of when to go for online learning and when to go for batch or offline learning. What is Batch Learning? Batch learning represents the training of machine learning models in a batch manner. The data get accumulated over a period of time. The models then get trained with the accumulated data from time to …
Scikit-learn vs Tensorflow – When to use What?
In this post, you will learn about when to use Scikit-learn vs Tensorflow. For data scientists/machine learning enthusiasts, it is very important to understand the difference such that they could use these libraries appropriately while working on different business use cases. When to use Scikit-learn? Scikit-learn is a great entry point for beginners data scientists. It provides an efficient implementation of many machine learning algorithms. In addition, it is very simple and easy to use. You can get started with Scikit-learn in a very easy manner by using Jupyter notebook. Scikit-learn can be used to solve different kinds of machine learning problems including some of the following: Classification (SVM, nearest neighbors, random …
Data Science Architect Interview Questions
In this post, you will learn about interview questions that can be asked if you are going for a data scientist architect job. Data science architect needs to have knowledge in both data science/machine learning and cloud architecture. In addition, it also helps if the person is hands-on with programming languages such as Python & R. Without further ado, let’s get into some of the common questions right away. I will add further questions in the time to come. Q. How do you go about architecting a data science or machine learning solution for any business problem? Solving a business problem using data science or machine learning based solution can …
Drivetrain Approach for Machine Learning
In this post, you will learn about a very popular approach or methodology called as Drivetrain approach coined by Jeremy Howard. The approach provides you a process to design data products that provide you with actionable outcomes while using one or more machine learning models. The approach is indeed very useful for data scientists/machine learning enthusiasts at all levels. However, this would prove to be a great guide for data science architects whose key responsibility includes designing the data products. Without further ado, let’s do a deep dive. Why drivetrain approach? Before getting into the drivetrain approach and understands the basic concepts, Lets understand why drivetrain approach in the first …
Machine Learning – Training, Validation & Test Data Set
In this post, you will learn about the concepts of training, validation, and test data sets used for training machine learning models. The post is most suitable for data science beginners or those who would like to get clarity and a good understanding of training, validation, and test data sets concepts. The following topics will be covered: Data split – training, validation, and test data set Different model performance based on different data splits Data Splits – Training, Validation & Test Data Sets You can split data into the following different sets and each data split configuration will have machine learning models having different performance: Training data set: When you …
Why use Random Seed in Machine Learning?
In this post, you will learn about why and when do we use random seed values while training machine learning models. This is a question most likely asked by beginners data scientist/machine learning enthusiasts. We use random seed value while creating training and test data set. The goal is to make sure we get the same training and validation data set while we use different hyperparameters or machine learning algorithms in order to assess the performance of different models. This is where the random seed value comes into the picture. Different Python libraries such as scikit-learn etc have different ways of assigning random seeds. While training machine learning models using Scikit-learn, …
