Specialization Deep learning

Высший рейтинг на Coursera
В любой момент
5 месяцев
Стоимость курса
49 USD/мес.
Подробности и регистрация

Specialization Deep learning

Высший рейтинг на Coursera
Навыки, которые вы получите:
Deep learning Tensorflow Artificial neural Neural network architecture Backpropagation Mathematical optimization Python

The Deep Learning Specialization is a foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology.

In this Specialization, you will build and train neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, Transformers, and learn how to make them better with strategies such as Dropout, BatchNorm, Xavier/He initialization, and more. Get ready to master theoretical concepts and their industry applications using Python and TensorFlow and tackle real-world cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more.

AI is transforming many industries. The Deep Learning Specialization provides a pathway for you to take the definitive step in the world of AI by helping you gain the knowledge and skills to level up your career. Along the way, you will also get career advice from deep learning experts from industry and academia.

Necessary preparation

  • Intermediate Python skills: basic programming, understanding of for loops, if/else statements, data structures.
  • A basic grasp of linear algebra & ML.

The Program

  1. Нейронные сети и глубокое обучение.
  2. Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization.
  3. Structuring Machine Learning Projects.
  4. Convolutional Neural Networks.
  5. Sequence Models.

What will you learn

  • Build and train deep neural networks, identify key architecture parameters, implement vectorized neural networks and deep learning to applications.
  • Train test sets, analyze variance for DL applications, use standard techniques and optimization algorithms, and build neural networks in TensorFlow.
  • Build a CNN and apply it to detection and recognition tasks, use neural style transfer to generate art, and apply algorithms to image and video data.
  • Build and train RNNs, work with NLP and Word Embeddings, and use HuggingFace tokenizers and transformer models to perform NER and Question Answering.
Нам нужен ваш фидбек!
Честный и беспристрастный