Unanswered Questions
139 questions with no upvoted or accepted answers
6
votes
1
answer
144
views
It is possible to use deep learning to give approximate solutions to NP-hard graph theory problems?
It is possible to use deep learning to give approximate solutions to NP-hard graph theory problems?
If we take, for example, the travelling salesman problem (or the dominating set problem). Let's say ...
CommunityBot
- 1
4
votes
0
answers
74
views
Why does a neural network struggle to solve this simple problem?
Consider the following problem:
Given a vector x of size dim with values between 0 and 1 (exclusive), determine if ...
- 201
4
votes
0
answers
1k
views
Can we combine multiple different neural networks in one?
I want to make a kind of robotic brain, i.e. a big neural network, which includes an NLP model (for understanding human voice), real-time object recognition system (so that it can identify particular ...
- 42.4k
4
votes
0
answers
193
views
Can AlexNet be changed to produce floating-point outputs in the range $[-1, 1]$, and, if not, which model should I use?
I'm developing a game AI, which tries to master racing simulation. I already trained a CNN (AlexNet) on in-game footage of me playing the game and the pressed keys as the target.
I had two main issues ...
- 42.4k
3
votes
0
answers
148
views
Why shouldn't batch normalisation layers be learnable during fine-tuning?
I have been reading this TensorFlow tutorial on transfer learning, where they unfroze the whole model and then they say:
When you unfreeze a model that contains ...
- 42.4k
3
votes
0
answers
272
views
Understanding the TensorFlow implementation of the policy gradient method
I was trying to understand the implementation of a basic policy gradient (REINFORCE) method using TensorFlow.
I think I got almost everything. The only thing that still bothers me is the loss function ...
- 42.4k
3
votes
0
answers
499
views
How to use TPU for real-time low-latency inference?
I use Google's Cloud TPU hardware extensively using Tensorflow for training models and inference, however, when I run inference I do it in large batches. The TPU takes about 3 minutes to warm up ...
- 103
3
votes
0
answers
401
views
How do I create a chatbot using tensorflow or pytorch using like the one defined in dialogflow?
How do I create a chatbot using TensorFlow or PyTorch using like the one defined in DialogFlow? What are the best datasets that I can use so to create my own personal assistant like google assistant?
...
- 2,859
3
votes
0
answers
1k
views
Applying a 1D convolution for 4D input
i'm trying to implement this paper and I'm stuck for quite some time now. Here is the issue:
I have a 3D tensor and has (180,200,20) as dimension and I'm trying ...
3
votes
0
answers
30
views
How to voxelize multiple frames at the time and append them together?
I'm trying to implement this approach for object detection and tracking.
In this approach, the first step is voxelize each frame to construct a 3D tensor, the second step is to append multiple voxels ...
- 42.4k
3
votes
0
answers
737
views
Getting worse performance when training a pre-trained model with the existing class
I am training pre-trained SSD-InceptionV2-Coco to detect the "car",
which is one of the classes in mscoco label.
I train the model with ~50k sample from KITTI, 500k iteration with batch size 2.
I ...
- 131
3
votes
1
answer
217
views
If neurons are only defined for values between 0 and 1, how does ReLU differ from the identity?
I'm struggling to understand the underlying mechanics of CNNs so any help is appreciated. I have a network with a ReLU activation function which does perform signifigantly better than one with sigmoid....
CommunityBot
- 1
2
votes
0
answers
141
views
How to Create a Neural Network Model to Generate Dance Movements Based on Music in MMD Format
I am working on a project where I need to create a neural network model to generate dance movements based on music. My goal is to achieve results similar to this video: https://youtu.be/FrA7f5F9TsI
...
- 101
2
votes
0
answers
271
views
cGAN: Discriminator loss going to zero while Generator's going always up but the result is very good
I have a Conditional Generative Adversarial Network for Quantum State Tomography. The metrics I am monitoring during the training process are the losses and the Fidelity (the degree of similarity ...
- 785
2
votes
0
answers
37
views
Combining GANs and NLP for AI-Based Programming: Generating Input-Output Templates for Computer Functions
I would like to combine GANs and NLP to create a system that can take an input and generate an appropriate output. For example, ...
- 21