Machine Learning Guide, or MLG, is a machine learning podcast built as an audio course for beginners and managers: the models, from linear regression to neural networks, plus the math and the tools. A curated resource list at ocdevel.com/mlg/resources gives the step-by-step learning path. Links Notes and resources at ocdevel.com/mlg/1 Join the free MLG group: listen to my other AI shows, ask me questions, and talk with other listeners What Machine Learning Guide covers Models: shallow learning (linear and logistic regression, naive Bayes, decision trees) and deep learning (neural networks, convolutional and recurrent neural networks). Math: the calculus, statistics and linear algebra machine learning needs, at a high level. Tools: languages and frameworks such as Python, TensorFlow, scikit-learn and PyTorch. Each topic goes as deep as audio allows. Details that need a visual are left to textbooks and videos. Who the podcast is for People learning machine learning, often to move into the field from another one. The host, Tyler Renelle, came from web and mobile development with a bachelor's in computer science, taught himself and got work in the field. Doing the same takes rigor and a structured list of resources. Managers and executives who want enough to judge which technologies fit a project, or to talk with their machine learning and data science staff. The MLG resources list The resources list is that structured list. It orders what to take step by step and filters by format (audiobook, textbook, video, course), price and quality. It includes well-known starting points like Andrew Ng's Coursera course and fast.ai, plus other machine learning podcasts. MLG and MLA episodes The feed has two kinds of episodes. Machine Learning Guide (MLG) covers theory and concepts. Machine Learning Applied (MLA) is hands-on: languages and frameworks, tech stacks, cloud deployment and the job hunt (interviews, salaries). Next: what AI, machine learning and data science are.
