Bienvenidos
IPN-Dharma IA Lab
Es una iniciativa de Laboratorio de Inteligencia Artificial del CIC del IPN con la colaboración de DHARMA para motivar a investigadores, profesores y estudiantes a aprovechar los cursos, recursos y herramientas de las principales plataformas tecnológicas de la industria en las áreas de Aprendizaje Automático, Ciencia de Datos, Computación en la Nube, Inteligencia Artificial e Internet de las Cosas con el propósito de generar una experiencia práctica a través de un modelo de aprendizaje entre pares y por objetivos.
Nivel 2: Conocimiento Contextual
Machine Learning
Are you ready to start practicing machine learning? Learn and apply fundamental machine learning concepts with the Crash Course, Google's fast-paced, practical introduction to machine learning, a self-study guide for aspiring machine learning practitioners. Then, continue with other courses that will allow you to delve into this exciting topic.
Cursos en este programa
1) Machine Learning Crash Course with TensorFlow APIs
This course teaches the basics of machine learning through a series of lessons that include video lectures from researchers at Google, text written specifically for newcomers to ML, interactive visualizations of algorithms in action and real-world case studies. While learning new concepts, you'll immediately put them into practice with coding exercises that walk you through implementing models in TensorFlow, an open-source machine intelligence library.
Some of the questions answered in this course:
Some of the questions answered in this course:
- How does machine learning differ from traditional programming?
- What is loss, and how do I measure it?
- How does gradient descent work?
- How do I determine whether my model is effective?
- How do I represent my data so that a program can learn from it?
- How do I build a deep neural network?
Esfuerzo estimado 15 horas
Idioma inglés
2) Introduction to Machine Learning Problem Framing
Welcome to Introduction to Machine Learning Problem Framing! This course helps you frame machine learning (ML) problems. This course does not cover how to implement ML or work with data.
Course Learning Objectives:
Course Learning Objectives:
- Define common ML terms.
- Describe examples of products that use ML and general methods of ML problem-solving used in each.
- Identify whether to solve a problem with ML.
- Compare and contrast ML to other programming methods.
- Apply hypothesis testing and the scientific method to ML problems.
- Have conversations about ML problem-solving methods.
3) Data Preparation and Feature Engineering for Machine Learning
Machine learning helps us find patterns in data—patterns we then use to make predictions about new data points. To get those predictions right, we must construct the data set and transform the data correctly. This course covers these two key steps. We'll also see how training/serving considerations play into these steps.
Course Learning Objectives:
Course Learning Objectives:
- Recognize the relative impact of data quality and size to algorithms.
- Set informed and realistic expectations for the time to transform the data.
- Explain a typical process for data collection and transformation within the overall ML workflow.
- Collect raw data and construct a data set.
- Sample and split your data set with considerations for imbalanced data.
- Transform numerical and categorical data.
4) Clustering in Machine Learning
The clustering self-study is an implementation-oriented introduction to clustering.
Course Learning Objectives:
Course Learning Objectives:
- Define clustering for ML applications.
- Prepare data for clustering.
- Define similarity for your dataset.
- Compare manual and supervised similarity measures.
- Use the k-means algorithm to cluster data.
- Evaluate the quality of your clustering result.
5) Recommendation Systems
Welcome to Recommendation Systems! We've designed this course to expand your knowledge of recommendation systems and explain different models used in recommendation, including matrix factorization and deep neural networks.
Course Learning Objectives:
Course Learning Objectives:
- Describe the purpose of recommendation systems.
- Understand the components of a recommendation system including candidate generation, scoring, and re-ranking.
- Use embeddings to represent items and queries.
- Develop a deeper technical understanding of common techniques used in candidate generation.
- Use TensorFlow to develop two models used for recommendation: matrix factorization and softmax.
6) Testing and Debugging in Machine Learning
Welcome to Testing and Debugging in Machine Learning! Testing and debugging machine learning systems differs significantly from testing and debugging traditional software. This course describes how, starting from debugging your model all the way to monitoring your pipeline in production.
Course Learning Objectives:
Course Learning Objectives:
- Validate raw feature data and engineered feature data.
- Debug a ML model to make the model work.
- Implement tests that simplify debugging.
- Optimize a working ML model.
- Monitor model metrics during development, launch, and production.
7) Generative Adversarial Networks
Generative adversarial networks (GANs) are an exciting recent innovation in machine learning. GANs are generative models: they create new data instances that resemble your training data. This course covers GAN basics, and also how to use the TF-GAN library to create GANs.
Course Learning Objectives:
Course Learning Objectives:
- Understand the difference between generative and discriminative models.
- Identify problems that GANs can solve.
- Understand the roles of the generator and discriminator in a GAN system.
- Understand the advantages and disadvantages of common GAN loss functions.
- Identify possible solutions to common problems with GAN training.
- Use the TF GAN library to make a GAN.