Creada por:   Universidad de Toronto

  • Geoffrey Hinton

    Enseñado por:    Geoffrey Hinton, Professor

    Department of Computer Science
Cómo aprobarAprueba todas las tareas calificadas para completar el curso.
Calificaciones del usuario
4.5 stars
Average User Rating 4.5Ve los que los estudiantes dijeron

Preguntas Frecuentes
Cómo funciona
Trabajo del curso
Trabajo del curso

Cada curso es como un libro de texto interactivo, con videos pregrabados, cuestionarios y proyectos.

Ayuda de tus compañeros
Ayuda de tus compañeros

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.

Universidad de Toronto
Established in 1827, the University of Toronto has one of the strongest research and teaching faculties in North America, presenting top students at all levels with an intellectual environment unmatched in depth and breadth on any other Canadian campus.
Calificaciones y revisiones
Calificado 4.5 de 5 907 calificaciones

The first 10 lectures, while quite theoretical, are very useful to most people learning Deep Learning for practical tasks. Last few lectures are heavily focused on RBMs and might not be immediately relevant, but are great for the historical perspectives and for people interested in more advanced aspects of Deep Learning.

Thanks Hinton and all other stuff for the great course. I spent less than one month in learning and passing this course. I don't know if I am the one quickest. I am sure I have not got all knowledge points and I will continue working on and will make deeper understanding in future work. But, I did pass it in such a short time. I was very challenge journey. I would like to share how I made it.

1) I did investigation on Linear algebra and Statistics for about 1 years that helps me a lot in understanding the math (such conditional possibility, PCA etc. ) quickly.

2) Before taking this course, I learned Andrew Ng's Machine Learning course. It helped me a lot in understanding the basic concept of learning theory.(such as overfitting etc.. ) . Without that experience, I would have not pass this course so quickly.

3) I did programming work for many year though I am a fresh hand on Octave. It makes coding work is not that much challenging.

Very up to date and challenging.

Only drawback, not a lot of application and octave/matlab is good for a fast mathematical implementation but not for real application with python packages for example.

Thanks Prof. Hinton for taking the time to make these insights publicly available!

This is a very thorough introductory course to the field of Machine Learning. I would have given it 5 stars, but towards the end, I felt the lessons got a bit sloppier. New concepts not thoroughly explained, sloppier slides, and even a lecture video missing at one point (had to find a link to it on youtube)! Still a very solid, instructive course, though. Recommended!