This is the Introductory Module to the Deep Learning Course at CDS, a course that covered the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition.

Difficulty level: Intermediate

Duration: 50:17

Speaker: : Yann LeCun and Alfredo Canziani

This module covers the concepts of gradient descent and the backpropagation algorithm and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:51:03

Speaker: : Yann LeCun

This lecture covers the concept of parameter sharing: recurrent and convolutional nets and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:59:47

Speaker: : Yann LeCun and Alfredo Canziani

This lecture covers the concept of convolutional nets in practice and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 51:40

Speaker: : Yann LeCun

This lecture discusses the concept of natural signals properties and the convolutional nets in practice and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:09:12

Speaker: : Alfredo Canziani

This lecture covers the concept of recurrent neural networks: vanilla and gated (LSTM) and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:05:36

Speaker: : Alfredo Canziani

This lecture is a foundationational lecture for the concept of energy-based models with a particular focus on the joint embedding method and latent variable energy-based models (LV-EBMs) and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:51:30

Speaker: : Yann LeCun

This lecture covers the concept of inference in latent variable energy based models (LV-EBMs) and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:01:04

Speaker: : Alfredo Canziani

This lecture is a foundationational lecture for the concept of energy-based models with a particular focus on the joint embedding method and latent variable energy based models (LV-EBMs) and is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:48:53

Speaker: : Yann LeCun

This tutorial covers the concept of training latent variable energy based models (LV-EBMs) and is is a part of the Deep Learning Course at NYU's Center for Data Science.

Difficulty level: Intermediate

Duration: 1:04:48

Speaker: : Alfredo Canziani

Course:

This lecture covers the rationale for developing the DAQCORD, a framework for the design, documentation, and reporting of data curation methods in order to advance the scientific rigour, reproducibility, and analysis of data.

Difficulty level: Intermediate

Duration: 17:08

Speaker: : Ari Ercole

The Medical Informatics Platform (MIP) is a platform providing federated analytics for diagnosis and research in clinical neuroscience research. The federated analytics is possible thanks to a distributed engine that executes computations and transfers information between the members of the federation (hospital nodes). In this talk the speaker will describe the process of designing and implementing new analytical tools, i.e. statistical and machine learning algorithms. Mr. Sakellariou will further describe the environment in which these federated algorithms run, the challenges and the available tools, the principles that guide its design and the followed general methodology for each new algorithm. One of the most important challenges which are faced is to design these tools in a way that does not compromise the privacy of the clinical data involved. The speaker will show how to address the main questions when designing such algorithms: how to decompose and distribute the computations and what kind of information to exchange between nodes, in order to comply with the privacy constraint mentioned above. Finally, also the subject of validating these federated algorithms will be briefly touched.

Difficulty level: Intermediate

Duration: 20:26

Speaker: : Jason Skellariou

- Clinical neuroinformatics (7)
- Standards and Best Practices (2)
- Bayesian networks (1)
- Machine learning (9)
- Neuroimaging (6)
- EBRAINS RI (2)
- Neuromorphic engineering (3)
- Standards and best practices (4)
- Tools (11)
- Workflows (3)
- Brain-hardware interfaces (1)
- (-) Clinical neuroscience (3)
- (-) General neuroscience (9)
- Computational neuroscience (28)
- Statistics (3)
- Computer Science (2)
- Genomics (7)
- (-) Data science (3)
- (-) Open science (5)
- Project management (1)