Questions tagged [deep-learning]

For questions related to deep learning, which refers to a subset of machine learning methods based on artificial neural networks (ANNs) with multiple hidden layers. The adjective deep thus refers to the number of layers of the ANNs. The expression deep learning was apparently introduced (although not in the context of machine learning or ANNs) in 1986 by Rina Dechter in the paper "Learning while searching in constraint-satisfaction-problems".

Filter by
Sorted by
Tagged with
0
votes
1answer
95 views

What are the pros and cons of using a spatial transformation network to predict the next video frame?

I've read through a few papers on next frame prediction from a sequence of frames and several of them use spatial transformations (STNs). See this as an example. I want to know what are the pros and ...
6
votes
1answer
777 views

Is there ever a need to combine deep learning frameworks? (Eg. TensorFlow & Torch)?

Imagine a simple scenario of having a large repository using one framework and integrated with data/robots, etc., then having a new feature requested and the framework missing some vital functionality ...
1
vote
2answers
569 views

How many GPUs can these deep learning algorithms be parallelized across (batch parallelization)?

The deep learning algorithms I would to know the limits of are: CNTK Caffe TensorFlow Torch7 Theano For example: I've heard TensorFlow is near impossible to parallelize on 8 GPUs and above. So, in ...
5
votes
1answer
108 views

How can one find / collect data for, and come up with ideas for, using Deep Learning / AI to improve one's everyday life?

I can see a lot of tutorials and examples about using TensorFlow and other free, open-source AI/ML/DL frameworks on enterprise level where enough data was collected for such AI solutions. How can one ...
7
votes
1answer
1k views

Are more than 8 high performance Nvidia GPUs practical for deep learning applications?

I was prompted towards this question while trying to find server racks and motherboards which are specialized towards artificial intelligence. Naturally I went to the SuperMicro website. There the ...
5
votes
1answer
712 views

Precise localization and characterization of rudimentary shapes with neural networks

I understand that there are flavors of (convolutional) neural networks that are useful for object localization and detection tasks of reasonable difficulty. In all of the examples I have seen so far, ...
2
votes
3answers
233 views

What type of AI would you recommend for this complex problem?

I'm trying to develop a kind of AI that will assist in debugging a large software system while we run test cases on it. The AI can get access to anything that the developers of the system can, namely ...
6
votes
1answer
441 views

How do neural networks manage to do regression?

I'm trying to learn about neural networks, and I'm interested in gaining a better conceptual understanding of how they work to solve certain problems. I'm having trouble in conceptually understanding ...
3
votes
1answer
3k views

Identifying cars using deep learning

I would like to use deep leaning for identifying cars; I want the system to predict wether an object is a car or not. How can I do that knowing that im still a beginner in the Deep Learning field ? I ...
1
vote
1answer
61 views

Can I limit the possible choices for a computer vision framework to recognize?

To risk giving away too much info, im building a piece of hardware with the job of identifying the object in front of it. If it can only be one of three different items, how can I tell the computer ...
5
votes
3answers
603 views

Use of machine learning for analyzing companies enlisted in stock market

Can current trends and tools, in the field of machine learning, replicate the complexity of financial market? If yes, then what are the tools available in this domain. Q. I am trying to build a model ...
1
vote
1answer
135 views

Reinforce Learning: Do I have to ignore hyper parameter(?) after training done in Q-learning?

Learner might be in training stage, where it update Q-table for bunch of epoch. In this stage, Q-table would be updated with gamma(discount rate), learning rate(alpha), and action would be chosen by ...
5
votes
1answer
101 views

Why is the change in cost wrt bias in neural network equal to error in the neuron?

While reading the book on neural networks by Michael Nielson, I had a problem understanding equation (BP3), which is $$ \frac{\partial C}{\partial b_{j}^{l}}=\delta_{j}^{l} \tag{BP3}\label{BP3}, $$ ...
2
votes
2answers
195 views

Are all breakthroughs in AI and machine learning are due to increase in computational resources?

I have read that all the math responsible for modern day machine learning and AI was already in place in 1900s but we did not have computational resources to implement those algorithms. So, is that ...
15
votes
2answers
1k views

When is deep learning overkill?

For example, for classifying emails as spam, is it worthwhile - from a time/accuracy perspective - to apply deep learning (if possible) instead of another machine learning algorithm? Will deep ...
12
votes
6answers
2k views

Is there actually a lack of fundamental theory on deep learning?

I heard several times that one of the fundamental/open problems of deep learning is the lack of "general theory" on it because actually we don't know why deep learning works so well. Even the ...
6
votes
4answers
497 views

What does deep learning offer with respect to standard machine learning?

I've been reading a lot about DL. I can understand to an extent how it works, in theory at least, and how it's technically different from conventional ML. But what I'm looking for is more of a "...
3
votes
1answer
698 views

Detect street and sidewalk surface in aerial imagery (neural network)

I would like to detect street and sidewalk surface in a very detailed (0.075m/pix) USGS High Resolution Orthoimagery which basically means image segmentation with two classes. Places in question are ...
2
votes
4answers
438 views

Training neural network for good taste in art

I'm a newbie in machine learning, so excuse me in advance). I have an idea to make NN that can estimate visual pleasantness of arbitrary image. Like you have a bunch of images that you like, you train ...
1
vote
2answers
8k views

Concatenate convolution layers with different strides in tensorflow.

I am trying to do an inception layer, but it only works if the convolution strides, pool strides and pool size are the same, otherwise I get an error in tf.concat that Dimesion 1 is not the same. ...
7
votes
3answers
726 views

Machine Learning hardware usage in embedded applications

I've been reading a lot about hardware development and implementation for AI/ML, mainly about Deep Learning, and I have a question about its usage. From what I understand, there are 2 stages for DL: ...
2
votes
1answer
116 views

Recognition of abbreviated text

I want to write a program that looks at abbreviated words, then figures out what the words are. For example, the abbreviation is "blk comp", and the translation is "black computer". In order to give ...
0
votes
1answer
186 views

Tensorboard problems

When trying to run tensorboard locally to show my logs with tensorboard --logdir logs/ it always shows nothing but the regular tensorboard menu options, such as ...
0
votes
2answers
3k views

Is it possible to run SSD or YOLO object detection on Raspberry Pi 3 for live object detection?

Is it possible to run SSD or YOLO object detection on Raspberry Pi 3 for live object detection (2/4frames x second)? I've tried this SSD implementation but it takes 14 s per frame. Is there anything I ...
11
votes
5answers
3k views

Why are deep neural networks and deep learning insufficient to achieve general intelligence?

Everything related to Deep Learning (DL) and deep(er) networks seems "successful", at least progressing very fast, and cultivating the belief that AGI is at reach. This is popular imagination. DL is a ...
2
votes
1answer
602 views

Why do action recognition algorithms perform better on ucf101dataset than HMDB51 dataset?

If we look at state of the art accuracy on the UCF101 data set, it is around 93% whereas for the HMDB51 data set it is around 66%. I looked at both the data sets and both contain videos of similar ...
12
votes
1answer
432 views

How can Viv generate new code based on some user's query?

I have been looking into Viv, an artificial intelligent agent in development. Here is a demonstration of Viv (by Dag Kittlaus). Based on what I understand, this AI can generate new code and execute it ...
1
vote
0answers
100 views

Infer dependent variables to produce output aligned to trained data

Hypothetical example, say I wanted: P(gender,ethnicity|age,hair); so that the input would aligned to a trained dataset of: ...
2
votes
5answers
2k views

Is it a good idea to pay for an deep learning course? [closed]

I'm an artificial intelligence enthusiastic and I want to learn about it. I want to ask you what do you think about the Udacity nanodegree Deep Learning Nanodegree Foundation. I don't know if it is ...
5
votes
1answer
674 views

Using crowdsourcing for deep learning

Most companies dealing with deep learning (automotive - Comma.ai, Mobileye, various automakers etc.) do collect large amounts of data to learn from and then use lots of computational power to train a ...
4
votes
2answers
82 views

How can I design an AI that knows when its being spoken to?

I am trying to make an intelligent agent similar to Jarvis from Iron Man, but much less complex. However, I want my AI to be able to determine if I am talking to it or not. So, I plan on having it ...
5
votes
5answers
368 views

How would AI be able to self-examine?

As I see some cases of machine-learning based artificial intelligence, I often see they make critical mistakes when they face inexperienced situations. In our case, when we encounter totally new ...
5
votes
2answers
366 views

Feasibility of generating large images with a convnet

I've spent the past couple of months learning about neural networks, and am thinking of projects that would be fun to work on to cement my understanding of this tech. One thing that came to mind last ...
2
votes
0answers
106 views

Conversational agent,query [closed]

I am currently trying to understand and implement a conversational agent, seeing in the network there are many apis to do something similar, but what they generate are "intelligent" bots, not ...
4
votes
4answers
380 views

Which methods or algorithms to develop a learning application?

I am creating a game application that will generate a new level based on the performance of the user in the previous level. The application is regarding language improvement, to be precise. Suppose ...
0
votes
2answers
221 views

Is it possible to train deep learning agent to pass a multiple-choice exam?

Is it possible to train an agent to take and pass a multiple-choice exam based on a digital version of a textbook for some area of study or curriculum? What would be involved in implementing this and ...
4
votes
1answer
1k views

Dataset containing images of varying dimensions and orientations

I am new to deep learning. I have a dataset of images of varying dimensions of a certain object. A few images of the object are also in varying orientations. The objective is to learn the features ...
3
votes
1answer
487 views

Is there any good app for iOS or Android to create, train and run neural networks? [closed]

Is there any good app for iOS or Android to create, train and run neural networks? I know there is NeuralMesh for the web, but I want something similar offline.
3
votes
0answers
97 views

How is the distribution of the state related to the distribution of the units in Boltzmann machines?

I'm trying to understand Boltzmann machines. Tutorials explain it with two formulas. Logistic function for the probability of single units: $$p(unit=1)=\frac{1}{1+e^{-\sum_{x}wx } }$$ and, when the ...
2
votes
1answer
183 views

Network representation for Q-Learning in carrom

I am trying to build an agent to play carrom. The problem statement is roughly to estimate three parameters (normalized) : force angle of striker position of strike Since the state and action ...
2
votes
0answers
123 views

What resources are good for learning to program AI? [closed]

I know how to program. I've familiar with C++, Python, and Java, and I've known how to program for years now. I've experimented with genetic algorithms, but I want to go further. What resources should ...
33
votes
3answers
25k views

Why is Lisp such a good language for AI?

I've heard before from computer scientists and from researchers in the area of AI that that Lisp is a good language for research and development in artificial intelligence. Does this still apply, with ...
13
votes
2answers
2k views

How are generative adversarial networks trained?

I am reading about generative adversarial networks (GANs) and I have some doubts regarding it. So far, I understand that in a GAN there are two different types of neural networks: one is generative ($...
9
votes
2answers
518 views

Was DeepMind's DQN Atari game learning simultaneous?

DeepMind state that their deep Q-network (DQN) was able to continually adapt its behavior while learning to play 49 Atari games. After learning all games with the same neural net, was the agent ...
12
votes
1answer
2k views

How would DeepMind's new differentiable neural computer scale?

DeepMind just published a paper about a differentiable neural computer, which basically combines a neural network with a memory. The idea is to teach the neural network to create and recall useful ...
3
votes
3answers
539 views

AI becoming sentient plausibility?

In lots of sci-fi, it seems that AI becomes sentient (Terminator, Peter F Hamilton's SI (commonwealth saga), etc.) However, I'm interested in whether this is actually plausible, whether an AI could ...
7
votes
1answer
378 views

What is the most abstract concept learned by a deep neural network?

It seems that deep neural networks are making improvements largely because as we add nodes and connections, they are able to put together more and more abstract concepts. We know that, starting from ...
2
votes
3answers
4k views

When using neural networks to detect features in an image, how can locate that specific feature in the original image?

I understand how a neural network can be trained to recognise certain features in an image (faces, cars, ...), where the inputs are the image's pixels, and the output is a set of boolean values ...
74
votes
3answers
52k views

How can neural networks deal with varying input sizes?

As far as I can tell, neural networks have a fixed number of neurons in the input layer. If neural networks are used in a context like NLP, sentences or blocks of text of varying sizes are fed to a ...
14
votes
2answers
720 views

Should deep residual networks be viewed as an ensemble of networks?

The question is about the architecture of Deep Residual Networks (ResNets). The model that won the 1-st places at "Large Scale Visual Recognition Challenge 2015" (ILSVRC2015) in all five main tracks: ...