+ Create new tricision Login 

Login



Forgot password?

First visit? Sign-up now!

By continuing you accept the Terms & Conditions and Privacy Policy.

time is up

Topics and questions to discuss during the Q&A sessions of the DLTM workshop.

saved
Ideas
Pros and cons
 
Votes
What are the tasks deep learning can and cannot solve.
by Francois Fleuret
 
39

Laleh, amina, Pierre-Alexandre and 36 more

What are the insights on choosing a deep learning architecture for a particular task?
by Andre Anjos
35

amina, Pierre-Alexandre, Serife and 32 more

What are the limitations of the current deep learning frameworks.
by Francois Fleuret
31

Laleh, amina, Pierre-Alexandre and 28 more

How do you interpret (gain insight) from what the network learns
by Carlos Peña
20

Thibault GROUEIX, amina, Pierre-Alexandre and 17 more

How much performance improvement in practice comes from hyperparameter tuning as opposed to exploring different e.g. deeper architectures?
18

Darshan, Michaël, Paulina G. and 15 more

What are the unavoidable trade-offs when designing a deep-learning framework.
by Francois Fleuret
16

Luca Baldassarre, Anaïs Badoual, Armand Valsesia and 13 more

What are good recommendations to gather sufficient data (variability) to train a particular deep learning architecture? More is better always?
by Andre Anjos
14

Amir Mohammadi, Young Joo Seo, Pierre-Alexandre and 11 more

What is the most promising challenger among other machine learning techniques.
by Francois Fleuret
14

amina, Pierre-Alexandre, Serife and 11 more

What optimization method would you recommend using to train a neural network? SGD, Adagrad, Adam, LBFGS, w/o momentum, ...
by Aurelien Lucchi
11

Young Joo Seo, amina, Serife and 8 more

Are there aspects of deep learning that still lack theoretical foundations?
by Pedro Gusmao
10

Damien, amina, Serife and 7 more

How should the academic value of a new architecture be judged?
by Florian S.
10

Serife, James Newling, Cijo Jose and 7 more

What is the scale of the brute-force grid-search for meta-parameters at Google and Facebook.
by Francois Fleuret
9

Young Joo Seo, Damien, Olivier and 6 more

Are there non-disputable and non-trivial similarities between deep-learning architectures and biological systems.
by Francois Fleuret
 
Can we come up with new engineering ideas in DNN field by studying biological systems? Are there ... more
by Tulyakov
8

amina, Cijo Jose, Michael and 5 more

When do we use deep neural network compared to other machine learning technique.
by Ateneken
8

Damien, Serife, Stepan Tulyakov and 5 more

What are the expected "solved task" milestones in the 1, 3 and 10 years horizons.
by Francois Fleuret
6

Pierre-Edouard, James Newling, Cijo Jose and 3 more

How can we exploit Reinforcement learning in Deep Architectures? What do we need to make it actually work?
by Prodromos
6

Pierre-Alexandre, Michael, Tulyakov and 3 more

What are the current limitations of RNN's and how do memory based models solve them?
by Jason Ramapuram
6

Gulcan, Young Joo Seo, Sébastien Piccand and 3 more

What are the books any deep-learning practitioner must have read.
by Francois Fleuret
5

Reinforcement learning, Michael, Sara Sedlar and 2 more

What are potentials and limitations of transfer learning in deep neural networks? How different datasets and tasks between the base and target network could be?
by Sara Sedlar
5

LI Xuhong, Michael, Tulyakov and 2 more

How well is deep learning performing with online training
by Alex Nanchen
5

Pierre-Alexandre, Pierre-Edouard, Sara Sedlar and 2 more

Deep learning for NLP - state-of-the-art network architectures, limitations, data representation (word-level, character-level, N-grams of words or characters, ...), word embeddings
by Jasmina
4

amina, Pierre-Alexandre, Maxime Darçot and 1 more

Should AlexNet/CNN features now be taken for granted and used as HOG/SIFT?
by Olivier Canévet
4

Gulcan, Cijo Jose, Francois Fleuret and 1 more

Will deep learning architectures be deeper and deeper in the future?
by Paolo russo
4

Ivan Štajduhar, Stepan Tulyakov, Hesam Setareh and 1 more

Is there any computational-intensive deep-learning task/algorithm which cannot be easily accelerated with GPUs.
by Mikhail Asiatici
4

James Newling, Sofiane Sarni, Sara Sedlar and 1 more

Is there a future for mass-market deep-learning specific hardware.
by Francois Fleuret
4

Olivier, Tiago, Cijo Jose and 1 more

Does deep learning creates a need for new engineer profiles.
by Francois Fleuret
4

Pierre-Alexandre, Olivier, James Newling and 1 more

The idea of growing neural networks was very popular in the early 90's, for example the famous cascade-correlation. But now the trend is to use fixed large capacity networks. Do you see a future in growing networks?, if not why?
by Cijo Jose
 
I think it is similar to my question about not predefined structure.
by Stepan Tulyakov
3
James
Olivier
Stepan Tulyakov
Deep learning's success in due in part to (1) improved algorithms (2) improved hardware and (3) more abundant data. Please rank the importance of these 3 factors. Does your importance ranking match current research budgets, and should it?
by James Newling
3
Cijo Jose
James
Olivier
Adversarial Examples (Szegedy '14) : (1) what does their existence suggest, and (2) how can we best use them?
by James Newling
3
James
Olivier
Tatjana Chavdarova
How successful are DNN with not predefined structure? It there any progress with such DNNs?
by Tulyakov
3
Mikhail Asiatici
Olivier
Tulyakov
What is recent progress, future prospecive and difficulties with semi-supervised and unsupervised learning with DNN
by Tulyakov
3
amina
Gulcan
Tulyakov
What is the most principled way of comparing two DL architectures?
by Tatjana Chavdarova
3
Olivier
Sara Sedlar
Serife
How will the interactions between the private sector and the academic world evolve.
by Francois Fleuret
3
El Mahdi El Mhamdi
Francois Fleuret
Marta Martinez
What are the key deep learning factors for good generalisation ? The amount of data ? Sparse representations ? Depth ? Objective function ? etc.
by Sébastien Piccand
3
Luca Baldassarre
Sara Sedlar
Tiago
Which is the more simple (in terms of coding and use) framework for Deep Learning?
by Fotini
3
Anaïs Badoual
Olivier
Tulyakov
Do you see a potential for FPGAs in deep learning.
by Mikhail Asiatici
3
Mikhail Asiatici
Olivier
Serife
How much does driving the learning process help ? e.g. Pre training some first layers for manifold learning; adding layers for specific tasks (alignment, normalization, feautre reduction); and finally adding final layers for some final decision.)
by Sébastien Piccand
 
This could be counter productive and limit the capabilities of the deep architecture.
 
This could make the learning process faster as it simplifies the big picture.
2
amina
James
Is there a sound alternative to "baby-sitting the learning rate/the experiment"?
by Olivier
2
Cijo Jose
James
What are the current ideas/strategies in the deep learning community to create networks being able to do one-shot learning?
by Michael
2
El Mahdi El Mhamdi
Gulcan
What is the pros and cons of the deep learning libraries; Theano, Tensorflow, Caffe and Torch7?
by Young Joo Seo
1
Thibault Groueix
Are there theory-grounded rules to determine the ideal size of a DNNetwork?
by El Mahdi El Mhamdi
1
amina
What are the recent advances in zero-shot/one-shot learning/ data-efficient learning with DNNs/RNNs? What are the future prospects in these tasks?
by Gulcan Can
0
In theory, what are the characteristics of a self-supervised task(if there is any) through which convnet learns richer representations than ones it learns via human supervision? In practice, what challenges do we need to address to implement such tasks?
by Mehdi Noroozi
0
Is RTRL still a valid solution to online problems (Since all modern ML RNN training algorithms use BPTT) ?
by Jason Ramapuram
0

Comments

Foteini

Which is the more simple/easy in framework for Deep Learning?

Mon, Jun 27, 2016

http://www.tricider.com/brainstorming/38Q6gxl5sNZ