Questions tagged [deep-neural-networks]

For questions related to deep neural networks, which are artificial neural networks with "many" layers, where "many" can vary depending on the context.

Filter by
Sorted by
Tagged with
0
votes
0answers
23 views

My Deep Q-Learning Network does not learn for OpenAI gym's cartpole problem

I am implementing OpenAI gym's cartpole problem using Deep Q-Learning (DQN). I followed tutorials (video and otherwise) and learned all about it. I implemented a code for myself and I thought it ...
0
votes
0answers
20 views

What is the state-of-the-art algorithm for neural style transfer?

I've read the paper A Neural Algorithm of Artistic Style by Gatys et. al. and I find the application of neural style transfer very fun. I also read that Exploring the structure of a real-time, ...
0
votes
0answers
30 views

Why do we use the Target Network for action evaluation in Double deep Q networks

Is there any specific reason as to why The target Network is used for evaluation and The online network Is used for selection, what would be the difference if both roles were switched, our online ...
0
votes
0answers
40 views

Is it known how neural networks work? [duplicate]

There was a chess neural network AlphaZero that taught itself how to play chess better than any chess program that has been created before in just 4 hours. I'm not asking to have it explained to me ...
0
votes
1answer
53 views

Why does not the deepAR model of Amazon require the time series being stationary, as opposed to ARMA model?

As what the title said. Does not deepAR require the time series being stationary?
0
votes
0answers
43 views

Possible reasons that validation recall is fluctuating across different epochs but the precision is stable?

I'm training a deep learning model. After each epoch I measure the performance of the model on validation set. Here is how the performance looks like while training: It's a binary classification task ...
2
votes
1answer
60 views

How does the target network in double DQNs find the maximum Q* value for each action?

I understand the fact that the neural network is used to take the states as inputs and it outputs the Q-value for state-action pairs. However, in order to compute this and update its weights, we need ...
1
vote
0answers
36 views

How can one be sure that a particular neural network architecture would work?

Traditionally, when working with tabular data, one can be sure(or at least know) that a model works because the included features could explain a target variable, say "Price of a ticket" ...
1
vote
0answers
46 views

Advantages of training Neural Networks based on analytic success criteria

What is the reason to train a Neural Network to estimate a task's success (i.e. robotic grasp planning) using a simulator that is based on analytic grasp quality metrics? Isn't a perfectly trained NN ...
1
vote
1answer
54 views

Why do we need target network in deep Q learning? [duplicate]

I already know deep RL, but to learn it deeply I want to know why do we need 2 networks in deep RL. What does the target network do? I now there is huge mathematics into this, but I want to know deep ...
0
votes
0answers
29 views

DQN Tic-Tac-Toe does not quite become optimal

I am trying to implement a DQN agent for playing standard 3x3 Tic-Tac-Toe (it is a double DQN with experience replay, and using a target network). I got the hyperparameters to the point where the ...
0
votes
0answers
22 views

Computational difference between ANN and Pattern Matching

Conceptually, if you had an internal 3d model of all objects in CV you could do a scan matching algorithm. This algorithm would be ridiculously computationally intensive, but it would have a high ...
0
votes
0answers
32 views

Why are YOLO Darknet weights so heavy?

I have been trying to understand how YOLO Darknet works, and for the most part reading the documentation and checking the code helps me understand. But when it comes to the weight file, I can't find ...
0
votes
0answers
16 views

Separated LSTMs or a global one for cluster of related features

I have an $n$-dimensional time-series to apply LSTM to, $n$ is the number of features for each time point. These features can be clustered according to their concept, for example $n_1, ..., n_4$ are ...
1
vote
1answer
55 views

Can we use a pre trained Encoder (BERT, XLM ) with a Decoder (GPT, Transformer-XL) to build a Chatbot instead of Language Translation?

I was wondering if the BART or T5 models can do the task of generating sentences in English. Most of the models I have mentioned ...
3
votes
1answer
47 views

What's the right way of building a deep Q-network?

I'm new to RL and to deep q-learning and I have a simple question about the architecture of the neural network to use in an environment with a continous state space a discrete action space. I tought ...
1
vote
0answers
80 views

Understanding the role of the target network in this DQN algorithm

I've found online this interesting algorithm: From what I understand reading this algorithm, I can't figure out why I should "perform the opposite action" and consequently storing that second ...
1
vote
0answers
26 views

How can I find the similar non-zero connections between different levels of sparsity of the same network?

I am pruning a neural network (CNN and Dense) and for different sparsity levels, I have different sub-networks. Say for sparsity levels of 20%, 40%, 60% and 80%, I have 4 different sub-networks. Now, ...
1
vote
1answer
40 views

Random value generator using a single neuron or DNN

AI is supposed to do anything human or traditional computer can do, that is what we expect AI to be. So 'generating random value' is also a task included in the scope that AI should be able to do I'...
0
votes
0answers
16 views

How to stabilize the training of a Conv-Siamese Neural Network if the results after different trainings vary relatively strongly?

I am training a neural network using MSE and ADAM optimizer. More precisely, a siamese architecture with a convolutional encoder and euclidean distance on top. I am using MSE because I have different ...
0
votes
0answers
19 views

Deep Network with constraint or auxiliary features

The target of my current neural network is to predict a label. The dataset contains some features, there is a label $y_i$ in transaction $i$, indicating its classification. There is one feature $f^{i}...
2
votes
0answers
33 views

Why Pixel RNN (Row LSTM) can capture triangular contexts?

I'm reading the paper Pixel Recurrent Neural Network. I have a question about Row LSTM. Why Row LSTM can capture triangular contexts? In this paper, the kernel of the one-dimensional convolution ...
3
votes
0answers
43 views

Are there any commonly used discontinuous activation functions?

Are there any commonly used activation functions (e.g. that take values in $(0,.5)\cup (.5,1)$)? Preferably for classification? Why? I was looking for commonly used activation functions on Google, ...
1
vote
1answer
31 views

How to use convolution neural network in Deep-Q?

I currently have a grid of pixels 20x20. Each pixel can be red green blue or black. So I have one hot-encoded the pixels giving a 20x20x4 array for each screen. For my Deep-Q Network, I have ...
3
votes
1answer
114 views

How to detect vanishing gradients?

Edit: I've reworked my question to generalize better and be more on-topic, and be mostly software implementation agnostic. Can vanishing gradients be detected by the change in distribution (or lack ...
1
vote
0answers
26 views

Steps to train and re-train a good model

I'm still a bit new to deep learning. What I'm still struggling, is what is the best practice in re-training a good model over time? I've trained a deep model for my binary classification problem (...
1
vote
2answers
52 views

Training accuracy vs validation accuracy on deep models

I'm training a deep network in Keras on some images for a binary classification (I have around 12K images). Once in a while, I collect some false positives and add ...
1
vote
0answers
20 views

Post-classification after inference

I designed a fire detection using Deep Learning based classification approach. In my training dataset, I have both fire and fire smokes are supposed to be detected (all under "fire"; mostly real fires ...
1
vote
1answer
94 views

How many layers exists in my neural network?

I have a neural network model defined as below. How many layers exist there? Not sure which ones to count when we are asked about the number. ...
1
vote
1answer
39 views

Multiple GPUs one expensive GPU, which gpu to buy for real time processing (not training)

I am trying to decide what GPU or GPUs to buy to run tf-pose pose detection and yolo3 object detection on several cameras. I need to keep an acceptable frame rate too. what kind of GPU configuration ...
1
vote
0answers
15 views

Can a trained Vid2Vid model be run on AMDs Ryzen 2700x with 32GB of RAM?

I know that training deep neural networks (DNNs) takes a lot of computational resources. This is, of course, just a generalized statement. Different networks require different resources. One that I ...
1
vote
0answers
38 views

Relationship between model complexity (depth) and dataset size

I'm new to deep learning. I was wondering what's the relationship between a deep model complexity (e.g. total number of parameters, or depth) and the dataset size? Assuming I want to do a binary ...
1
vote
0answers
104 views

Should I use deep learning to solve my task?

I need to predict the performance (CPI cycles-per-instruction) of 90 machines for the next hour (or day). Each machine has a thousand records (e.g. CPU and memory usage). Currently, I am using a ...
2
votes
2answers
106 views

what will i be able to do in the end of AI: modern approach? [closed]

i just started the book and i was wondering , what will i be able to do in AI by the end of the book ? and more particularly, what is my position with Reinforcement Learning, deep neural networks and ...
2
votes
1answer
468 views

What is the difference between Kaldi and DeepSpeech speech recognition systems in their approach?

I would like to know how do Kaldi and DeepSpeech speech recognition systems differ algorithmically? Which one would be more accurate for continuous speech in time?
0
votes
1answer
32 views

Techniques and semantics in better training of deep learning models

I'm relatively new to Deep Learning, and trying various models and datasets using Keras. I'm starting to love it! Through-out my experimentations, I have come into ...
3
votes
1answer
66 views

Can Google's patented ML algorithms be used commercially?

I just find that Google patents some of the widely used machine learning algorithms. For example: System and method for addressing overfitting in a neural network (Dropout?) Processing images using ...
2
votes
1answer
57 views

Is there anything theoretically revolutionary about Deep Neural Network?

In recent years we have seen quite a lot of impressive display of Deep Neural Network (DNN), as demonstrated most famously by AlphaGo and its cousin programs. But if I understand correctly, deep ...
2
votes
0answers
44 views

Which deep neural networks are appropriate for the detection of bombs?

This is a follow-up question from my previous post here about explosion detection. I gathered a dataset of explosions. As I'm new to Deep Learning in Keras, I'm trying to see what architecture best ...
3
votes
1answer
197 views

Is it possible to create a decompiler using AI?

I am trying to decode a compiled file to source code and I am failing. I want to know whether an AI based decompilation is possible for a compiled files? Is it possible to create a decompiler using a ...
3
votes
1answer
69 views

Is batch normalization not suitable for non-gaussian input?

I generate some non-Gaussian data, and use two kinds of DNN models, one with BN and the other without BN. I find that the model DNN with BN can't predict well. The codes is shown as follow: <...
1
vote
1answer
25 views

Are there deep networks that can differentiate object class from individual object?

We usually categorize objects in a hierarchy of classes. Let us say crow vs bird. In addition, classes can be "messy", for instance a crow can be also a predator, but not all birds are predators. My ...
0
votes
1answer
33 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] ]; ...
0
votes
1answer
98 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
34 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
46 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, ...
2
votes
1answer
52 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
0answers
27 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 ...
3
votes
4answers
247 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 ...
4
votes
2answers
328 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 ...