Acerca de este curso: >>> By enrolling in this course you agree to the End User License Agreement as set out in the FAQ. Once enrolled you can access the license in the Resources area <<< This course, Applied Artificial Intelligence with DeepLearning, is part of the IBM Advanced Data Science Certificate which IBM is currently creating and gives you easy access to the invaluable insights into Deep Learning models used by experts in Natural Language Processing, Computer Vision, Time Series Analysis, and many other disciplines. We’ll learn about the fundamentals of Linear Algebra and Neural Networks. Then we introduce the most popular DeepLearning Frameworks like Keras, TensorFlow, PyTorch, DeepLearning4J and Apache SystemML. Keras and TensorFlow are making up the greatest portion of this course. We learn about Anomaly Detection, Time Series Forecasting, Image Recognition and Natural Language Processing by building up models using Keras one real-life examples from IoT (Internet of Things), Financial Marked Data, Literature or Image Databases. Finally, we learn how to scale those artificial brains using Kubernetes, Apache Spark and GPUs. IMPORTANT: THIS COURSE ALONE IS NOT SUFFICIENT TO OBTAIN THE "IBM Watson IoT Certified Data Scientist certificate". You need to take three other courses where two of them are currently built. The Specialization will be ready late spring, early summer 2018 Using these approaches, no matter what your skill levels in topics you would like to master, you can change your thinking and change your life. If you’re already an expert, this peep under the mental hood will give your ideas for turbocharging successful creation and deployment of DeepLearning models. If you’re struggling, you’ll see a structured treasure trove of practical techniques that walk you through what you need to do to get on track. If you’ve ever wanted to become better at anything, this course will help serve as your guide. Prerequisites: Some coding skills are necessary. Preferably python, but any other programming language will do fine. Also some basic understanding of math (linear algebra) is a plus, but we will cover that part in the first week as well. If you choose to take this course and earn the Coursera course certificate, you will also earn an IBM digital badge. To find out more about IBM digital badges follow the link ibm.biz/badging.
Para quién es esta clase: Data Scientists who want to master Deep Learning and AI, Developers who want to get their hands dirty with the most promising technology of this century
Enseñado por: Romeo Kienzler, Chief Data Scientist, Course Lead
IBM Watson IoTEnseñado por: Niketan Pansare, Senior Software Engineer
IBM ResearchEnseñado por: Tom Hanlon, Training Director
SkymindEnseñado por: Max Pumperla, Deep Learning Engineer
Enseñado por: Ilja Rasin, Data Scientist
IBM Watson Health
| Información básica | Curso 3 de 4 en Advanced Data Science with IBM Specialization |
| Nivel | Avanzado |
| Compromiso | 4 weeks of study, 4-6 hours/week |
| Idioma | English |
| Cómo aprobar | Aprueba todas las tareas calificadas para completar el curso. |
| Calificaciones del usuario |
- Reading: IBM Digital Badge
- Vídeo: Introduction - Romeo Kienzler
- Vídeo: Introduction - Ilja Rasin
- Vídeo: Introduction - Niketan Pansare
- Vídeo: Introduction - Tom Hanlon
- Vídeo: Course Logistics
- Reading: Video summary on environment setup
- Reading: Where to get all the code and slides for download?
- Vídeo: Cloud Architectures for AI and DeepLearning
- Vídeo: Linear algebra
- Vídeo: Deep feed forward neural networks
- Vídeo: Convolutional Neural Networks
- Vídeo: Recurrent neural networks
- Vídeo: LSTMs
- Vídeo: Auto encoders and representation learning
- Vídeo: Methods for neural network training
- Vídeo: Gradient Descent Updater Strategies
- Vídeo: How to choose the correct activation function
- Vídeo: The bias-variance tradeoff in deep learning
- Reading: Introduction to ApacheSpark (optional)
- Reading: Link to Github
- Vídeo: Neural Network Debugging with TensorBoard
- Vídeo: Automatic Differentiation
- Vídeo: Introduction video
- Vídeo: Keras overview
- Vídeo: Sequential models in keras
- Vídeo: Feed forward networks
- Vídeo: Recurrent neural networks
- Vídeo: Beyond sequential models: the functional API
- Vídeo: Saving and loading models
- Vídeo: What is SystemML (1/2) ?
- Vídeo: What is SystemML (2/2) ?
- Vídeo: Demo - How to use Apache SystemML on IBM DSX (1/3)
- Vídeo: Demo - How to use Apache SystemML on IBM DSX (2/3)
- Vídeo: Demo - How to use Apache SystemML on IBM DSX (3/3)
- Vídeo: Introduction to DeepLearning4J
- Vídeo: Demo: Running Java in Data Science Experience
- Vídeo: DL4J Neural Network Code Example, Mnist Classifier
- Vídeo: PyTorch Installation
- Vídeo: PyTorch Packages
- Vídeo: Tensor Creation and Visualization of Higher Dimensional Tensors
- Vídeo: Math Computation and Reshape
- Vídeo: Computation Graph, CUDA
- Vídeo: Linear Model
- Reading: Link to files in Github
- Vídeo: How to implement an anomaly detector (1/2)
- Vídeo: How to implement an anomaly detector (2/2)
- Vídeo: How to deploy a real-time anomaly detector
- Vídeo: Introduction to Time Series Forecasting
- Vídeo: Stateful vs. Stateless LSTMs
- Vídeo: Batch Size
- Vídeo: Number of Time Steps, Epochs, Training and Validation
- Vídeo: Trainin Set Size
- Vídeo: Input and Output Data Construction
- Vídeo: Designing the LSTM network in Keras
- Vídeo: Anatomy of a LSTM Node
- Vídeo: Number of Parameters
- Vídeo: Training and loading a saved model
- Vídeo: Classifying the MNIST dataset with Convolutional Neural Networks
- Vídeo: Image classification with Imagenet and Resnet50
- Vídeo: Autoencoder - understanding Word2Vec
- Vídeo: Text Classification with Word Embeddings
- Reading: Link to Github
- Reading: Parallel Neural Network Training
- Vídeo: Creating and Scaling a Keras Model in ApacheSpark using DL4J
- Vídeo: Creating and Scaling a Keras Model in ApacheSpark using DL4J (Demo)
- Cuestionario de práctica: Run a Notebook using Keras and DL4J
- Vídeo: Scale TensorFlow with IBM Watson Machine Learning
- Vídeo: Computer Vision with IBM Watson Visual Recognition
- Vídeo: Text Classification with IBM Watson Natural Language Classifier
- Reading: Link to Github
Cada curso es como un libro de texto interactivo, con videos pregrabados, cuestionarios y proyectos.
Conéctate con miles de estudiantes y debate ideas y materiales del curso, y obtén ayuda para dominar los conceptos.
Obtén reconocimiento oficial por tu trabajo y comparte tu éxito con amigos, compañeros y empleadores.
| Comprar curso | |
|---|---|
| Accede a los materiales del curso | Disponible |
| Accede a los materiales con calificación | Disponible |
| Recibe una calificación final | Disponible |
| Obtén un Certificado de curso para compartir | Disponible |
Part with DeepLearning4J is not very good...
n/a
I like very much the architecture-based approach of these courses/ specialization.
At the end, the goal of an Enterprise, in a general sense, is to satisfy the local or global community necessity in an effective and efficient way. Surreally with the choose of the correct technology, frameworks, languages, instructions, details.... but , at the end, what is really important is the value offered.
That said, I think, that this specialization, provides the mindset, the knowledge, the skills and tools applicable in a corporate environment. Technology is important, yes, but, from my point of view, it is most important to consider the value that is emerging from the holistic approach of all the topics in the different modules of the courses, including also the final capstone project.
Thank you very much Romeo and all instructors for this continuous learning professional opportunity
S
Very good data science specialization covering many interesting advanced technologies!