The course will teach you how to develop deep learning models using Pytorch. The course will start with Pytorch's tensors and Automatic differentiation package. Then each section will cover different models starting off with fundamentals such as Linear Regression, and logistic/softmax regression. Followed by Feedforward deep neural networks, the role of different activation functions, normalization and dropout layers. Then Convolutional Neural Networks and Transfer learning will be covered. Finally, several other Deep learning methods will be covered. Learning Outcomes: After completing this course, learners will be able to: • explain and apply their knowledge of Deep Neural Networks and related machine learning methods • know how to use Python libraries such as PyTorch for Deep Learning applications • build Deep Neural Networks using PyTorch
Este curso faz parte do Certificado Profissional IBM AI Engineering
Deep Neural Networks with PyTorch
oferecido por
Programa - O que você aprenderá com este curso
Semana
15 horas para concluir
Tensor and Datasets
6 vídeos (Total 44 mín.), 1 leitura, 11 testes
6 videos
1.1 Tensors 1D13min
1.2 Two-Dimensional Tensors9min
Differentiation in PyTorch5min
1.3 Simple Dataset7min
1.5 Dataset4min
1 leituras
Labs10min
5 exercícios práticos
1.1 Tensors 1D5min
1.2 Two-Dimensional Tensors5min
1.3 Derivatives in PyTorch5min
Simple Dataset5min
Datasets10min
Semana
22 horas para concluir
Linear Regression
7 vídeos (Total 35 mín.), 10 testes
7 videos
2.1 Linear Regression Training3min
Loss3min
Gradient Descent4min
Cost3min
Linear Regression PyToch5min
PyTorch Linear Regression Training Slope and Bias5min
7 exercícios práticos
Prediction in One Dimension5min
Linear Regression Training5min
Loss5min
Gradient Descent5min
Cost5min
Training Parameters in PyTorch5min
PyTorch Linear Regression Training Slope and Bias5min
3 horas para concluir
Linear Regression PyTorch Way
5 vídeos (Total 21 mín.), 8 testes
5 videos
Mini-Batch Gradient Descent3min
Optimization in PyTorch3min
Training, Validation and Test Split4min
Training, Validation and Test Split PyTorch3min
4 exercícios práticos
Quiz: Stochastic Gradient Descent5min
Mini-Batch Gradient Descent5min
3.3 Optimization in PyTorch5min
Training and Validation Data PyTorch5min
Semana
32 horas para concluir
Multiple Input Output Linear Regression
4 vídeos (Total 18 mín.), 6 testes
4 videos
Multiple Linear Regression Training2min
Linear Regression Multiple Outputs5min
Multiple Output Linear Regression Training1min
2 exercícios práticos
Multiple Linear Regression Prediction5min
Multiple Output Linear Regression5min
2 horas para concluir
Logistic Regression for Classification
4 vídeos (Total 31 mín.), 8 testes
4 videos
5.1 Logistic Regression: Prediction6min
Bernoulli Distribution and Maximum Likelihood Estimation5min
Logistic Regression Cross Entropy Loss10min
5 exercícios práticos
5.0 Linear Classifiers5min
5.0 Linear Classifiers5min
5.1 Logistic Regression: Prediction10min
Bernoulli Distribution and Maximum Likelihood Estimation5min
5.3 Logistic Regression Cross Entropy Loss10min
Semana
42 horas para concluir
Softmax Rergresstion
3 vídeos (Total 18 mín.), 5 testes
3 exercícios práticos
6.1 Softmax Function:Using Lines to Classify Data5min
6.2 Softmax Prediction5min
6.3 Softmax PyTorch Quizz5min
3 horas para concluir
Shallow Neural Networks
6 vídeos (Total 33 mín.), 12 testes
6 videos
More Hidden Neurons2min
Neural Networks with Multiple Dimensional Input5min
7.4 Multi-Class Neural Networks5min
7.5 Backpropagation5min
7.5 Activation Functions4min
6 exercícios práticos
Neural Networks5min
More Hidden Neurons 5min
Neural Networks with Multiple Dimensional Inputs5min
Multi-Class Neural Networks5min
Backpropagation5min
Activation Functions5min
4.7
2 avaliaçõesPrincipais avaliações do Deep Neural Networks with PyTorch
Awesome! This course gives me the basic workflow for using machine learning technique in my research! The materials in the form of Jupyter lab really help!
Instrutores
Joseph Santarcangelo
Ph.D., Data Scientist at IBMIBM Developer Skills Network
Sobre IBM
IBM offers a wide range of technology and consulting services; a broad portfolio of middleware for collaboration, predictive analytics, software development and systems management; and the world's most advanced servers and supercomputers. Utilizing its business consulting, technology and R&D expertise, IBM helps clients become "smarter" as the planet becomes more digitally interconnected. IBM invests more than $6 billion a year in R&D, just completing its 21st year of patent leadership. IBM Research has received recognition beyond any commercial technology research organization and is home to 5 Nobel Laureates, 9 US National Medals of Technology, 5 US National Medals of Science, 6 Turing Awards, and 10 Inductees in US Inventors Hall of Fame.
Sobre Certificado Profissional IBM AI Engineering
The rapid pace of innovation in Artificial Intelligence (AI) is creating enormous opportunity for transforming entire industries and our very existence. After competing this comprehensive 6 course Professional Certificate, you will get a practical understanding of Machine Learning and Deep Learning.
You will master fundamental concepts of Machine Learning and Deep Learning, including supervised and unsupervised learning. You will utilize popular Machine Learning and Deep Learning libraries such as SciPy, ScikitLearn, Keras, PyTorch, and Tensorflow applied to industry problems involving object recognition and Computer Vision, image and video processing, text analytics, Natural Language Processing, recommender systems, and other types of classifiers.
You will be able to scale Machine Learning on Big Data using Apache Spark. You will build, train, and deploy different types of Deep Architectures, including Convolutional Networks, Recurrent Networks, and Autoencoders.
By the end of this Professional Certificate, you will have completed several projects showcasing your proficiency in Machine Learning and Deep Learning, and become armed with skills for a career as an AI Engineer.
Perguntas Frequentes – FAQ
Quando terei acesso às palestras e às tarefas?
Ao se inscrever para um Certificado, você terá acesso a todos os vídeos, testes e tarefas de programação (se aplicável). Tarefas avaliadas pelos colegas apenas podem ser enviadas e avaliadas após o início da sessão. Caso escolha explorar o curso sem adquiri-lo, talvez você não consiga acessar certas tarefas.
O que recebo ao me inscrever para este certificado?
Quando você se inscreve em um curso, ganha acesso a todos os cursos no certificado e obtém um certificado quando completar o trabalho. Seu certificado eletrônico pode ser adicionado à sua página de Participações, de onde você pode imprimi-lo ou adicioná-lo ao seu perfil no LinkedIn. Se quiser apenas ler e assistir o conteúdo do curso, pode participar como ouvinte sem custo.
Qual é a política de reembolso?
Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.
O Coursera proporciona acesso universal à melhor educação do mundo fazendo parcerias com as melhores universidades e organizações para oferecer cursos on-line.
© 2019 Coursera Inc. Todos os direitos reservados.
