Dive deep into the intricate universe of Artificial Intelligence with this in-depth learning path. This path is perfectly suited for those who wish to not only understand the theoretical aspects of Machine Learning algorithms but also wish to learn how to code these algorithms from scratch, without relying on common libraries such as Sklearn. You'll start with grasping the essence of Machine Learning, dissect the underlying principles, and then move on to implementing some of the most fundamental and crucial algorithms in ML all by yourself.
This learning path includes:
6 courses with bite-sized lessons and practices
26 engaging lessons in text and video formats
107 hands-on practices in our state-of-the art IDE
One-on-one guidance from Cosmo, our AI tutor
Dig deep into regression and learn about the gradient descent algorithm. This course does not rely on high-level libraries like scikit-learn, but focuses on building these algorithms from scratch for a thorough understanding. Master the implementation of simple linear regression, multiple linear regression, and logistic regression powered by gradient descent.
Go beneath the surface of classification algorithms and metrics, implementing them from scratch for deeper understanding. Bypass commonly-used libraries such as scikit-learn to construct Logistic Regression, k-Nearest Neighbors, Naive Bayes Classifier, and Decision Trees from ground up. This course includes creating the AUCROC metric for Logistic Regression, among others.
Delve into the intricacies of optimization techniques with this immersive course that focuses on the implementation of various algorithms from scratch. Bypass high-level libraries to explore Stochastic Gradient Descent, Mini-Batch Gradient Descent, and advanced optimization methods such as Momentum, RMSProp, and Adam.
Learn about Ensemble Methods and their implementation from scratch. This course covers the understanding and implementation of multiple ensemble methods such as Bagging, Random Forest, AdaBoost, and Gradient Boosting Machines like XGBoost without relying on high-level libraries.
Navigate through the intricacies of Unsupervised Learning and Clustering in this hands-on course. Skip the high-level libraries and build core aspects of unsupervised learning methods from scratch, including k-Means, mini-batch k-Means, Principal Component Analysis, and DBSCAN. Learn to assess cluster quality with crucial clustering metrics like homogeneity, completeness, and v-metric.
Dive deep into the theory and implementation of Neural Networks. This course will have you implementing tools at the heart of modern AI such as Perceptrons, activation functions, and the crucial components of multi-layer Neural Networks. All of this without the help of high-level libraries leaves you with a profound understanding of the underpinning mechanisms.
Our built-in AI guide and tutor, Cosmo, prompts you with challenges that are built just for you and unblocks you when you get stuck.