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 with TensorFlow on Google Cloud
What is machine learning, and what kinds of problems can it solve? What are the five phases of converting a candidate use case to be driven by machine learning, and why is it important that the phases not be skipped? Why are neural networks so popular now? How can you set up a supervised learning problem and find a good, generalizable solution using gradient descent and a thoughtful way of creating datasets?
Learn how to write distributed machine learning models that scale in Tensorflow, scale out the training of those models. and offer high-performance predictions. Convert raw data to features in a way that allows ML to learn important characteristics from the data and bring human insight to bear on the problem. Finally, learn how to incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems. You will experiment with end-to-end ML, starting from building an ML-focused strategy and progressing into model training, optimization, and productionalization with hands-on labs using Google Cloud Platform.
Learn how to write distributed machine learning models that scale in Tensorflow, scale out the training of those models. and offer high-performance predictions. Convert raw data to features in a way that allows ML to learn important characteristics from the data and bring human insight to bear on the problem. Finally, learn how to incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems. You will experiment with end-to-end ML, starting from building an ML-focused strategy and progressing into model training, optimization, and productionalization with hands-on labs using Google Cloud Platform.
Cursos en este programa
1) How Google does Machine Learning
What is machine learning, and what kinds of problems can it solve? Google thinks about machine learning slightly differently -- of being about logic, rather than just data. We talk about why such a framing is useful for data scientists when thinking about building a pipeline of machine learning models.
Then, we discuss the five phases of converting a candidate use case to be driven by machine learning, and consider why it is important the phases not be skipped. We end with a recognition of the biases that machine learning can amplify and how to recognize this.
What you will learn:
Then, we discuss the five phases of converting a candidate use case to be driven by machine learning, and consider why it is important the phases not be skipped. We end with a recognition of the biases that machine learning can amplify and how to recognize this.
What you will learn:
- Frame a business use case as a machine learning problem.
- Gain a broad perspective of machine learning and where it can be used.
- Convert a candidate use case to be driven by machine learning.
- Recognize biases that machine learning can amplify.
Esfuerzo estimado 9 horas
Idioma español e inglés
2) Launching into Machine Learning
Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of data science problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way that supports experimentation.
What you will learn:
What you will learn:
- Identify why deep learning is currently popular.
- Optimize and evaluate models using loss functions and performance metrics.
- Mitigate common problems that arise in machine learning.
- Create repeatable and scalable training, evaluation, and test datasets.
3) Introduction to TensorFlow
This course is focused on using the flexibility and “ease of use” of TensorFlow 2.x and Keras to build, train, and deploy machine learning models. You will learn about the TensorFlow 2.x API hierarchy and will get to know the main components of TensorFlow through hands-on exercises. We will introduce you to working with datasets and feature columns. You will learn how to design and build a TensorFlow 2.x input data pipeline. You will get hands-on practice loading csv data, numPy arrays, text data, and images using tf.Data.Dataset. You will also get hands-on practice creating numeric, categorical, bucketized, and hashed feature columns.
We will introduce you to the Keras Sequential API and the Keras Functional API to show you how to create deep learning models. We’ll talk about activation functions, loss, and optimization. Our Jupyter Notebooks hands-on labs offer you the opportunity to build basic linear regression, basic logistic regression, and advanced logistic regression machine learning models. You will learn how to train, deploy, and productionalize machine learning models at scale with Cloud AI Platform.
What you will learn:
We will introduce you to the Keras Sequential API and the Keras Functional API to show you how to create deep learning models. We’ll talk about activation functions, loss, and optimization. Our Jupyter Notebooks hands-on labs offer you the opportunity to build basic linear regression, basic logistic regression, and advanced logistic regression machine learning models. You will learn how to train, deploy, and productionalize machine learning models at scale with Cloud AI Platform.
What you will learn:
- Use the Keras Sequential and Functional APIs for simple and advanced model creation.
- Design and build a TensorFlow 2.x input data pipeline.
- Use the tf.data library to manipulate data and large datasets.
- Train, deploy, and productionalize ML models at scale with Cloud AI Platform.
4) Feature Engineering
Want to know how you can improve the accuracy of your ML models? What about how to find which data columns make the most useful features? Welcome to Feature Engineering where we will discuss good vs bad features and how you can preprocess and transform them for optimal use in your models.
What you will learn:
What you will learn:
- Compare the key required aspects of a good feature.
- Understand how to preprocess and explore features with Cloud Dataflow and Cloud Dataprep.
- Combine and create new feature combinations through feature crosses.
- Understand and apply how TensorFlow transforms features.
5) Art and Science of Machine Learning
Welcome to the Art and Science of machine learning. The course covers the essential skills of ML intuition, good judgment and experimentation needed to finely tune and optimize ML models for the best performance. You will learn how to generalize your model using Regularization techniques and about the effects of hyperparameters such as batch size and learning rate on model performance. We’ll cover some of the most common model optimization algorithms and show you how to specify an optimization method in your TensorFlow code.
What you will learn:
What you will learn:
- Generalize a ML model using Regularization techniques.
- Tune batch size and learning rate for better model performance.
- Optimize a ML model.
- Apply the concepts in TensorFlow code.