Introduction To Machine Learning | For VFX, Games And More | Pro Coding Course

Our journey into the world of Machine Learning has just begun with our newest coding course led by the exceptional Felipe Pezántes, whose previous hit course 'Python for Production' set the standard. This course will cover how Artificial Intelligence works and how to train one. We'll start with theory on how the field has evolved through the years and how the sub-fields are being developed, explored, and applied in our modern life. Regardless of any industry, AI and machine learning is one of the main components of most modern industries so we'll explore basic algorithms and check out how to develop using these modern technologies. Depending on the problem you're trying to solve, automate, or improve you'll see there are a ton of Machine Learning and AI architectures, models, and algorithms, that will impact your final product. There are so many resources for ML out there, so we'll have a proper main structure of what you need to know and where to go deeper at your choice. Course Page: https://www.rebelway.net/introduction-to-machine-learning Find Your Course: https://bit.ly/39IBlJX Here is a detailed weekly breakdown: Week 1: Intro to AI and AI subfields What is Machine Learning and what is AI Standard Software and Tools for AI/ML development Standard Hardware for AI/ML IPython and Jupyter Notebook Concepts and how to work with APIs Calculus: Intro to derivatives The chain rule Other calculus concepts intro to Linear Algebra Matrices concepts and python implementations Data and hardware Bitwise operations Week 2: SOLID principles for production code Memoization Intro to numpy GPU architectures Graph concepts Houdini and virtual environments Maze solver algorithm Intro to tensors Data structures Week 3: Intro to Data Web scrapping Useful resources for engineers intro to MLOPS Intro to Pandas Intro to Matplotlib Intro to Seaborn Exploratory Data Analysis NOIR concepts for Data Data pipelines Week 4: Intro to Machine Learning Supervised learning Linear Regression Training sets Intro to Scikit learn Multiple linear regression Evaluation metrics Logistic Regression Confusion Matrices ROC and AUC graphs Entropy Logistic regression in Houdini Week 5: Bias and Variance Partial derivatives Gradient Descent Learning Rate Supervised and unsupervised learning Feature Engineering: scaling, normalization, standarization ML models exploration Naive Bayes Decision Trees Random Forest K nearest neighbours Support Vector Machines Week 6: Vector stores, vector databases Unsupervised learning k means clustering Principal component analysis Recommender systems DBscan Fundamental concepts about: reducing loss Generalization Representation Regularization Ranking Efficiency Training a model Improving a model Advanced data concepts Houdini data visualization tools Week 7: Intro to Deep Learning Neural networks math, theory and implementations Neural Network architectures Basic neural network perceptrons Multi layer perceptrons Custom neural network model Activation Functions Backpropagation Neural networks in Houdini Convolutional Neural Networks Building neural networks Week 8: Intro to ML frameworks: Tensorflow Pytorch NN models with these libraries Cloud hubs Intro to production modeling Cloud services for ML A lot of experiments with Pytorch and Tensorflow Applied CUDA architectures for ML Week 9: Advanced model architectures ML ops in practice System design ML in production Intro to Docker Package a model Intro to transfer learning Model fine tuning Mixed precision Quantization Hardware accelerations Week 10: Intro to NLP NLP concepts and architectures Transformers intro and implementation intro to LLMs Fine tune LLms, applications like: Sentiment analysis Text translation Text autocomplete Text summarization Prompt engineering and in context learning Generative AI for NLPs First steps into Generative AI First steps into Computer Vision AI for Game development ML in Houdini

Видео Introduction To Machine Learning | For VFX, Games And More | Pro Coding Course автора Вероятности в розово-белых