Posts

Post has shared content

Public

Inspired by Google's inceptionism art, my colleagues made an interactive visualization of a dreaming convnet. It's pretty trippy!

Add a comment...

Post has shared content

Public

"Introduction to Neural Machine Translation", the second part is now up! http://devblogs.nvidia.com/parallelforall/introduction-neural-machine-translation-gpus-part-2/

Add a comment...

Post has attachment

Public

Add a comment...

Post has shared content

Public

Can we replace each convolution+pooling layer in the LeNet with a set of four recurrent neural nets? The answer is.. YES! Let me introduce you

http://arxiv.org/abs/1505.00393

**ReNet**+Francesco Visin +Kyle Kastner +Aaron Courville +Yoshua Bengiohttp://arxiv.org/abs/1505.00393

Add a comment...

Post has shared content

Public

Add a comment...

Post has shared content

Public

Announcing Theano 0.7

This is a release for a major version, with lots of new features, bug fixes, and some interface changes (deprecated or potentially misleading features were removed).

Upgrading to Theano 0.7 is recommended for everyone, but you should first make sure that your code does not raise deprecation warnings with the version you are currently using.

For those using the bleeding edge version in the git repository, we encourage you to update to the `rel-0.7` tag.

What's New:

* Integration of CuDNN for 2D convolutions and pooling on supported GPUs

* Too many optimizations and new features to count

* Various fixes and improvements to scan

* Better support for GPU on Windows

* On Mac OS X, clang is used by default

* Many crash fixes

* Some bug fixes as well

Description:

Theano is a Python library that allows you to define, optimize, and

efficiently evaluate mathematical expressions involving multi-dimensional arrays. It is built on top of NumPy. Theano features:

* tight integration with NumPy: a similar interface to NumPy's. numpy.ndarrays are also used internally in Theano-compiled functions.

* transparent use of a GPU: perform data-intensive computations up to 140x faster than on a CPU (support for float32 only).

* efficient symbolic differentiation: Theano can compute derivatives for functions of one or many inputs.

* speed and stability optimizations: avoid nasty bugs when computing expressions such as log(1+ exp(x)) for large values of x.

* dynamic C code generation: evaluate expressions faster.

* extensive unit-testing and self-verification: includes tools for detecting and diagnosing bugs and/or potential problems.

Theano has been powering large-scale computationally intensive scientific research since 2007, but it is also approachable enough to be used in the classroom (IFT6266 at the University of Montreal).

About Theano: http://deeplearning.net/software/theano/

Related projects: http://github.com/Theano/Theano/wiki/Related-projects

Machine Learning Tutorial with Theano on Deep Architectures:

http://deeplearning.net/tutorial/

Acknowledgments:

I would like to thank all contributors of Theano. For this particular release, many people have helped, and to list them all would be impractical.

I would also like to thank users who submitted bug reports.

Also, thank you to all NumPy and Scipy developers as Theano builds on

their strengths.

All questions/comments are always welcome on the Theano mailing-lists ( http://deeplearning.net/software/theano/#community )

This is a release for a major version, with lots of new features, bug fixes, and some interface changes (deprecated or potentially misleading features were removed).

Upgrading to Theano 0.7 is recommended for everyone, but you should first make sure that your code does not raise deprecation warnings with the version you are currently using.

For those using the bleeding edge version in the git repository, we encourage you to update to the `rel-0.7` tag.

What's New:

* Integration of CuDNN for 2D convolutions and pooling on supported GPUs

* Too many optimizations and new features to count

* Various fixes and improvements to scan

* Better support for GPU on Windows

* On Mac OS X, clang is used by default

* Many crash fixes

* Some bug fixes as well

Description:

Theano is a Python library that allows you to define, optimize, and

efficiently evaluate mathematical expressions involving multi-dimensional arrays. It is built on top of NumPy. Theano features:

* tight integration with NumPy: a similar interface to NumPy's. numpy.ndarrays are also used internally in Theano-compiled functions.

* transparent use of a GPU: perform data-intensive computations up to 140x faster than on a CPU (support for float32 only).

* efficient symbolic differentiation: Theano can compute derivatives for functions of one or many inputs.

* speed and stability optimizations: avoid nasty bugs when computing expressions such as log(1+ exp(x)) for large values of x.

* dynamic C code generation: evaluate expressions faster.

* extensive unit-testing and self-verification: includes tools for detecting and diagnosing bugs and/or potential problems.

Theano has been powering large-scale computationally intensive scientific research since 2007, but it is also approachable enough to be used in the classroom (IFT6266 at the University of Montreal).

About Theano: http://deeplearning.net/software/theano/

Related projects: http://github.com/Theano/Theano/wiki/Related-projects

Machine Learning Tutorial with Theano on Deep Architectures:

http://deeplearning.net/tutorial/

Acknowledgments:

I would like to thank all contributors of Theano. For this particular release, many people have helped, and to list them all would be impractical.

I would also like to thank users who submitted bug reports.

Also, thank you to all NumPy and Scipy developers as Theano builds on

their strengths.

All questions/comments are always welcome on the Theano mailing-lists ( http://deeplearning.net/software/theano/#community )

Add a comment...

Post has shared content

Public

An interview with Geoff Hinton, Yoshua Bengio and Yann LeCun in the latest talking machines podcast (by my good friends +Ryan Adams and Katy Gorman)

http://www.thetalkingmachines.com/

http://www.thetalkingmachines.com/

Add a comment...

Post has shared content

Public

Videos represent an abundant and rich source of (unsupervised) visual information. Extracting meaningful representations from large volumes of unconstrained video sequences in unsupervised fashion is quite challenging.

Here is one attempt at doing this, but I suspect more research will follow up very shortly.

http://arxiv.org/abs/1502.04681

Here is one attempt at doing this, but I suspect more research will follow up very shortly.

http://arxiv.org/abs/1502.04681

Add a comment...

Post has shared content

Public

Our new approach to construct deep RNNs:

Gated Feedback Recurrent Neural Networks.

http://arxiv.org/abs/1502.02367

Gated Feedback Recurrent Neural Networks.

http://arxiv.org/abs/1502.02367

Add a comment...

Post has shared content

Public

Montreal and Toronto join forces -- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.

http://arxiv.org/abs/1502.03044

http://arxiv.org/abs/1502.03044

Add a comment...

Wait while more posts are being loaded