Questions tagged [neural-network]
Use this tag for questions about possible applications of quantum computing in improving neural network models and/or quantum neural networks. Artificial neural networks (ANNs) or connectionist systems are computing systems vaguely inspired by the biological neural networks that constitute animal brains. Such systems "learn" (i.e. progressively improve performance on) tasks by considering examples, generally without task-specific programming (Wikipedia).
31
questions
1
vote
1
answer
73
views
Where is the input data X in the CV-QNN as presented in Pennylane?
I am referring to the tutorial of CV-QNN in Pennylane(Strawberry Fields).
Each layer of CV-QNN can perform the operation below.
Unlike other quantum neural network tutorials, where the input X and y ...
CommunityBot
- 1
0
votes
0
answers
24
views
Quantum data as input for Quantum Neural Net
I'm new to quantum machine learning, and I wanted to know how quantum data is processed in a quantum neural net.
For example, if I am training a QNN to classify entangled circuits from non-entangled ...
2
votes
0
answers
25
views
Quantum Convolutional Neural Network not producing gradients
I am trying to bulid a quantum convolutional neural network for image classification with Pennylane and Keras but the model isn't training and I keep getting the warning:
WARNING:tensorflow:Gradients ...
- 21
4
votes
0
answers
84
views
Equivalencies between neural networks and quantum neural networks
TL;DR - Quantum neural networks use a few qubits, gates and simple quantum circuits. Regular neural networks use real numbers (composed of many bits), nonlinear functions on real numbers and very ...
- 1,756
15
votes
5
answers
3k
views
Will deep learning neural networks run on quantum computers?
Deep Learning (multiple layers of artificial neural networks used in supervised and unsupervised machine learning tasks) is an incredibly powerful tool for many of the most difficult machine learning ...
2
votes
0
answers
96
views
How can we compute the gradient in a Quantum RNN?
I was looking into implementing a quantum recurrent neural network (QRNN) for a project, but I have some doubts about the computation of the gradient. There are a few papers that have implemented a ...
- 14.1k
1
vote
1
answer
1k
views
Hybrid Quantum LSTM in Qiskit
I read this article on a Hybrid Quantum LSTM in Pennylane and I'm trying to replicate it in Qiskit. Nevertheless it doesn't seem to work very well.
Here's my code
...
CommunityBot
- 1
1
vote
1
answer
140
views
Is this Quantum Neural Network overfitting?
In the accuracy graphs (attached the graph images below) shown in this code (Binary Classification for Fraud Detection):
validation loss is greater than training loss
training accuracy is greater ...
- 2,491
1
vote
1
answer
279
views
What are "unbounded loss functions" and "unbounded operators"?
I am reading this paper: Quantum Generative Training Using Rényi Divergences. In it, the authors mention the following multiple times:
"...an unbounded loss function can circumvent the existing ...
- 379
1
vote
1
answer
230
views
How could I choose cost function in Qiskit TwoLayerQNN?
So here is the problem, I've found that in a TwoLayerQNN, the backward gradient is only to minimize the expectation of observable I've chosen. But I'm not going to minimize the predict of the input, ...
4
votes
1
answer
3k
views
How is data encoded in a quantum neural network?
I am a newbie to quantum machine learning. I am trying to build a quantum neural network (QNN). What I studied so far about QNN is that input would be qubits and hidden layer parameter can be set ...
glS♦
- 24.8k
3
votes
1
answer
284
views
PennyLane operations - Kerr, Displacement and Squeeze
I am familiar with the quantum gates of Qiskit, but I become very confused when looking at the continuous variable (CV) operations in the PennyLane documentation. I am especially interested in the ...
- 859
1
vote
1
answer
364
views
Why is Farhi and Neven's architecture described in "Classification with Quantum Neural Network on near term processors" called a Neural Network?
In regards to "Classification with Quantum Neural Networks on near term processors" (which you can find here) , there are still a few things that do not make entirely sense to me.
First of all, why ...
glS♦
- 24.8k
10
votes
1
answer
662
views
Barren plateaus in quantum neural network training landscapes
Here the authors argue that the efforts of creating a scalable quantum neural network using a set of parameterized gates are deemed to fail for a large number of qubits. This is due to the fact that, ...
glS♦
- 24.8k
5
votes
1
answer
2k
views
Quantum Circuit To Compute Any Inner Product
I'm currently reading the paper Classification with Quantum Neural Networks on Near Term Processors
It shows a method to determine the following quantity:
Where U is a unitary operator acting on $|z,...
- 802
0
votes
1
answer
83
views
Question About Measuring an Operator For Quantum Neural Network Paper
I'm currently reading the paper: https://arxiv.org/pdf/1802.06002.pdf
I'm a little bit stuck on the step of how to determine the following quantity:
Where U is a unitary operator acting on $|z,1\...
CommunityBot
- 1
3
votes
1
answer
191
views
How is back-propagation done in "Transfer learning in hybrid classical-quantum neural networks"
Just read this paper from Xanadu on Quantum Transfer Learning and a couple of things are unclear to me regarding the optimisation step.
How is back-propagation done through the classical weights ...
- 859
1
vote
1
answer
91
views
Initial assumption of the unitary that allows us to estimate the label function
You can find the paper here , in which they describe the architecture of a QNN that can be used to learn binary functions and correctly classify unseen data.
They say that for each binary label ...
CommunityBot
- 1
5
votes
1
answer
151
views
Quantum NN vs Quantum-Inspired NN
I can't find the true difference between Quantum Neural Network (QNN) and Quantum-Inspired Neural Network (QINN).
I have multiple guesses:
QINN and QNN are absolutely the same thing (all QNNs are ...
glS♦
- 24.8k
2
votes
1
answer
385
views
How Mature is the Tensorflow Quantum Library [closed]
Where does The Tensorflow Quantum ( TFQ ) library fall on it's maturity curve.
In other words can we currently leverage the TFQ ...
- 695
11
votes
1
answer
367
views
Devising "structured initial guesses" for random parametrized quantum circuits to avoid getting stuck in a flat plateau
The recent McClean et al. paper Barren plateaus in quantum neural network training landscapes shows that for a wide class of reasonable parameterized quantum circuits, the probability that the ...
- 14.1k
2
votes
1
answer
179
views
Is there a quantum neural network "hello world" for character recognition (convolutional neural networks)?
I'm making my way through several neural network examples and libraries. Landing on this nugget, in creating a basic NN for character recognition.
In calculating weights and biases, looking at the ...
- 4,754
3
votes
0
answers
65
views
How to derive a circuit from given equations?
I was reading a paper on Quantum Neural Networks where the authors discussed a new back propagation algorithm. They shared a schematic of the circuit. However, I am unable to understand how the ...
- 4,927
5
votes
1
answer
596
views
How to encode MNIST data set on a quantum circuit to study supervised learning with QNN?
I am trying to implement arXiv:1802.06002†. I do not understand how to take the data set from MNIST and apply it to a quantum circuit.
[†]: Classification with Quantum Neural Networks on Near Term ...
- 17.5k
2
votes
1
answer
822
views
Can quantum annealing be used for training convolutional neural networks?
Simulated annealing is applied for deep learning using convolutional neural networks. Likewise, can quantum annealing be used?
These two papers:
Simulated Annealing Algorithm for Deep Learning (...
- 4,754
8
votes
1
answer
868
views
Quantum algorithm for linear systems of equations (HHL09): Step 1 - Number of qubits needed
This is a continuation of Quantum algorithm for linear systems of equations (HHL09): Step 1 - Confusion regarding the usage of phase estimation algorithm
Questions (contd.):
Part 2: I'm not exactly ...
CommunityBot
- 1
7
votes
1
answer
144
views
How did the authors manage to simulate and get the error estimate for a neural network with greater than 7840 qubits?
In the paper A quantum-implementable neural network model (Chen, Wang & Charbon, 2017), on page 18 they mention that "There are 784 qurons in the input layer, where each quron is comprised of ten ...
- 17.5k
7
votes
1
answer
351
views
Can quantum computing provide advantages related to Hardware-Neural Networks?
The following question is related to this one: Will deep learning neural networks run on quantum computers?. I found it complementary and necessary because the previous answers are not completely ...
- 17.5k
7
votes
0
answers
199
views
What do "$i$-th basic network", "quantum multiplexers" and "quantum parallelism" mean in this context? How are they beneficial?
I have been reading the paper A quantum-implementable neural network model (Chen et al., 2017) for a few days now, but failed to understand how exactly their algorithm offers a speedup over the ...
CommunityBot
- 1
9
votes
1
answer
588
views
Is it possible to speed up the generation of the weighting matrix using a quantum algorithm?
In this[1] paper, on page 2, they mention that they are generating the weighting matrix as follows:
$$W = \frac{1}{Md}[\sum_{m=1}^{m=M} \mathbf{x}^{(m)}\left(\mathbf{x}^{(m)}\right)^{T}] - \frac{\Bbb ...
- 3,686
6
votes
1
answer
209
views
What are some of the interesting problems whose solutions have been proposed using quantum neural networks?
I know there are some "quantum versions" of hand-writing recognition algorithms which have been proposed using quantum neural networks. Example: "Recognition of handwritten numerals by Quantum Neural ...
- 17.5k