Questions tagged [deep-network]

For questions about deep neural networks (DNNs), neural networks with multiple hidden layers between the input and output layer.

Filter by
Sorted by
Tagged with
11
votes
2answers
571 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: ...
0
votes
3answers
84 views

Is there a way of pre-determining whether a CNN model will perform better than another?

I developed a CNN for image analysis. I've around 100K labeled images. I'm getting a accuracy around 85% and a validation accuracy around 82%, so it looks like the model generalize better than ...
1
vote
1answer
38 views

In how few updates can a multi layer neural net be trained?

A single iteration of gradient descent can be parallelised across many worker nodes. We simple split the training set across the worker nodes, pass the parameters to each worker, each worker computes ...
0
votes
1answer
29 views

How to map X to Y for TensorFlow RNN training data

Usually for DNN, I have the training data of matching X (2D) to Y (2D), for example, XOR data: X = [[0,0],[0,1],[1,0],[1,1]]; Y = [[0], [1], [1], [0] ]; ...
-1
votes
1answer
25 views

Does higher Accuracy in Reinforcement Learning indicate better model performance?

If a reinforcement learning algorithm uses a Deep Neural Network to predict the action given a state (a NN for a policy function), an Monte Carlo Tree Search in a model-based learning setup, then ...
0
votes
2answers
22 views

Is it still called linear separation with a layer of more than 1 neuron

A single neuron will be able to do linear separation. For example, XOR simulator network: ...
0
votes
1answer
38 views

How many hidden layers are needed for this training data set

I'm trying to separate classes in 3D space, the data are as in the sketch below: There are 3 classes: 0,1,2; and with the look into the sketch, it seems that I need 3 planes to separate the classes, ...
9
votes
1answer
321 views

How much of a problem is white noise for the real-world usage of a DNN?

I read that deep neural networks can be relatively easily fooled (link) to give high confidence in recognition of synthetic/artificial images that are completely (or at least mostly) out of the ...
3
votes
2answers
30 views

What kind of output should be used for predicting angles in DNNs?

I am building a model which predicts angles as output. What are the different kinds of outputs that can be used to predict angles? For example, output the angle in radians cyclic nature of the ...
3
votes
4answers
185 views

What could an oscillating training loss curve represent?

I tried to create a simple model that receives an $80 \times 130$ pixel image. I only had 35 images and 10 test images. I trained this model for a binary classification task. The architecture of the ...
0
votes
0answers
23 views

Stacking layers with different input size in deep network

I am trying to design a deep network that works on signals. The network should include multiple stacked tasks, but each task would work on a different window size of the signal. For example, the ...
2
votes
1answer
28 views

Spikes in of Train and Test error

I learn a DNN for image recognition. During each epoch, I calculate mean loss in the training set. After each epoch, I calculate loss and number of errors over both training and test set. The problem ...
4
votes
2answers
319 views

Iteratively and adaptively increasing the network size during training

For an experiment that I'm working on, I want to train a deep network in a special way. I want to initialize and train a small network first, then, in a specific way, I want to increase network depth ...
0
votes
0answers
12 views

Camera pose to environment Mapping

I would like to teach a model the environment of a room. I'm doing so by mapping a camera pose (x, y, z, q0, q1, q2, q3) to its corresponding image; where x, y, z represent location in Cartesian ...
4
votes
1answer
43 views

How can I use one neural network for both players in Alpha Zero (Connect 4)?

First of all, it is great to have found this community! I am currently implementing my own Alpha Zero clone on Connect4. However, I have a mental barrier I cannot overcome. How can I use one neural ...
-1
votes
2answers
68 views

Contractive auto-encoders

I am trying to implement Contractive auto-encoders in PyTorch but I don't know what I'm doing is right or not. The architecture of the auto-encoder is given below: ...
6
votes
4answers
1k views

Which machine learning algorithm is used in self-driving cars?

Which deep neural network is used in Google's driverless cars to analyze the surroundings? Is this information open to the public?
1
vote
3answers
309 views

How to create Partially Connected NNs with prespecified connections using Tensorflow?

I'd like to implement a partially connected neural network with ~3 to 4 hidden layers (a sparse deep neural network?) where I can specify which node connects to which node from the previous/next layer....
8
votes
3answers
171 views

What is a deep neural network?

What is the definition of a deep neural network? Why are they so popular or important?
37
votes
5answers
2k views

What is fuzzy logic?

I'm new to A.I. and I'd like to know in simple words, what is the fuzzy logic concept? How does it help, and when is it used?
1
vote
1answer
25 views

Further Normalization of Standardized data - ANN

I want to develop a regression model using the artificial neural network. For developing such a model I use standardised ( z-score normalised ) data. given below is the sample data set. Here MAX is ...
2
votes
0answers
57 views

How to define cost function for custom nonlinear functions?

For logistic regression, the Cost function is defined as: \begin{equation} Cost(h_{\theta}(x)-y) = -ylog(h_{\theta}(x))-(1-y)log(1-h_{\theta}(x)) \end{equation} I now have a nonlinear function \begin{...
1
vote
2answers
62 views

How long it takes to train face recognition deep neural network? (rough estimation)

If I use a desktop PC with a GPU, how long it might take to train face recognition deep neural network on let's say dataset of 2.6 million images and 2600 identities? I guess it should depend on ...
1
vote
0answers
27 views

One end to end Neural network or many task-specific ones?

Is it better to train one neural network for a dispersed labeled data with large number of classes or first classify data by unsupervised learning then train each part by a separate NN? I mean by ...
3
votes
1answer
135 views

Can you learn parameters in nonlinear function?

In the paper Nonlinear Interference Mitigation via Deep Neural Networks, the the following network is illustrated. The network structure is The network parameters are $\theta = \{W_1^{1},...,W_1^{l-...
4
votes
0answers
373 views

Sparsity constraint in a deep autoencoder

Is there any way and any reason why one would introduce a sparsity constraint on a deep autoencoder? In particular, in deep autoencoders the first layer often has more units than the dimensionality ...
8
votes
2answers
614 views

What's the difference between hyperbolic tangent and sigmoid neurons?

Two common activation functions used in deep learning are the hyperbolic tangent function and the sigmoid activation function. I understand that the hyperbolic tangent is just a rescaling and ...
1
vote
0answers
38 views

What is the feasible neural network structure that can learn to identify types of trajectory of moving dots?

I have multiple image sequences, each of which contains an animation of two moving dots. The trajectory of the dots in a sequence is always cyclic (not necessarily circular). There are two types of ...
2
votes
3answers
1k views

What activation function is not used at the final layer of super resolution neural models?

I'm trying to implement some Image super-resolution models on medical images. After reading a set of papers, I found that none of the existing models use any activation layer for the last layer. What'...
4
votes
1answer
587 views

Suitable reward function for trading buy and sell orders

I am working to build an deep reinforcement learning agent which can place orders (i.e. limit buy and limit sell orders). The actions are ...
0
votes
0answers
37 views

How to use 0 padding with mask layer to handle variable lenght of my inputs in case of Multi-Layers Perceptrons?

We wanna build a DNN model to predict unrolling factor though our features represent variable length of inputs. Knowing that we have to give our features at once "0 padding" look like the only ...
24
votes
2answers
810 views

How is a deep neural network different from other neural networks?

How is a neural network having the "deep" adjective actually distinguished from other similar networks?
1
vote
0answers
33 views

How to handle varying length of inputs that represent dependencies and recursivity in deep neural networks in case of regression?

I wanna solve a problem of regression to predict a factor. I decide to go with Deep Neural Networks as solution for my problem. The features in this problem represent loop characteristic such us loop ...
3
votes
2answers
154 views

How to build my own dataset and model for an LSTM neural network

I have a sort of mathematical problem and I'm not sure which model I should choose to make an LSTM neural network. Currently in my country, there is a system in which certain groups of researchers ...
3
votes
1answer
94 views

Alpha zero before move 8

The Alpha zero paper says that the The first set of features are repeated for each position in a T = 8-step history. So what happens before the first 8 moves? Do they just repeat the starting position?...
1
vote
1answer
287 views

Deep Q-Learning poor convergence on Stochastic Environment

I'm trying to implement a Deep Q-network in Keras/TF that learns to play Minesweeper (our stochastic environment). I have noticed that the agent learns to play the game pretty well with both small and ...
2
votes
1answer
129 views

Significance of depth of a deep neural network

How is a feed-forward neural network with few hidden layers and lots of nodes in those hidden layers different from a network with a lot of hidden layers but relatively lesser nodes in those hidden ...
1
vote
1answer
135 views

Chess policy network

I am interested in making a simple chess engine using neural networks. I already have a fairly good value network but I can't figure out how to train a policy network. I know that Leela chess zero ...
3
votes
2answers
783 views

Is there any proof based literature out there on neural networks?

Is there any mathematical proof (like in proof of a theorem) based literature out there on neural networks ? Everything is empirically based but no math proof for instance on why certain parameters ...
28
votes
4answers
887 views

How to find the optimal number of neurons per layer?

When you're writing your algorithm, how do you know how many neurons you need per single layer? Are there any methods for finding the optimal number of them, or is it a rule of thumb?
5
votes
2answers
239 views

Is it possible to construct an ANN that is more efficient than the human brain?

Intelligence ... changes based on the environment and situation Human are now inventing machines exhibiting some features of their own Intelligence. There appears to be a possibility that, in the ...
2
votes
2answers
131 views

Should the actor or actor-target model be used to make predictions after training is complete (DDPG)?

The situation I am referring to the paper T. P. Lillicrap et al, "Continuous control with deep reinforcement learning" where they discuss deep learning in the context of continuous action spaces ("...
4
votes
3answers
182 views

What is the most time consuming part of training deep networks?

Deep networks notoriously take a long time to train. What is the most time consuming aspect of training them? Is it the matrix multiplications? Is it the forward pass? Is it some component of the ...
63
votes
9answers
5k views

How is it possible that deep neural networks are so easily fooled?

The following page/study demonstrates that the deep neural networks are easily fooled by giving high confidence predictions for unrecognisable images, e.g. How this is possible? Can you please ...
0
votes
1answer
194 views

Target values of 0.1 for 0 and 0.9 for 1 for sigmoid

I recently read an article about neural networks saying that, when using sigmoid as activation function, it's advised to use 0.1 as target value instead of 0, and 0.9 instead of 1. This was to avoid "...
5
votes
1answer
87 views

How can neural networks that extract many features be fooled by adversarial images?

I have been reading a bit about networks where deep layers able to deal with a bunch of features (be it edges, colours, whatever). I am wondering: how can possibly a network based on this '...
2
votes
0answers
22 views

Using two generative adversarial nets to classify articles - what is a good approach?

I'm trying to create a deep learning network to classify news article based on the text and associated image. The idea comes from a novel use of GANs to classify based on generated data. My approach ...
1
vote
0answers
67 views

Confidence interval around a DNN prediction

I am facing a problem and do not know whether it is even solvable: I want to predict the behaviour of a system using a DNN, say a CNN, in the sense that I want to predict the time and intensity of a ...
4
votes
1answer
2k views

Batch Normalization in Deep Autoencoders?

Does it make sense to use Batch Normalization in Deep (stacked) or/and Sparse Autoencoders? I cannot find any resources for that, so is it safe to assume that since it works for other DNNs it will ...
2
votes
1answer
34 views

Do Le et al. (2012) train all three autoencoder layers at a time, or just one?

Le et al. 2012 use a network of 1 billion parameters to learn neurons that respond to faces, cats, pedestrians, etc. without labels (unsupervised). Their network is built with three autoregressive ...