All Questions
Tagged with tensorflow neural-networks
96 questions
0
votes
0
answers
34
views
Predict more elements than the input
I can use any machine learning algorithms (but neural networks are better for me) to resolve this issue: use few elements as input (numerical) to predict more elements as output. In normal regression ...
- 101
2
votes
0
answers
111
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
...
- 21
0
votes
0
answers
13
views
Help With Converting NumPy Function To TensorFlow Ops (graph execution issue)
I'm trying to export my command recognition model for deploymenet on embedded devices, however, I'm facing trouble when trying to encapsulate the preprocessing function into my model, that way, when I ...
0
votes
1
answer
35
views
Why are the tutorials and built-in datasets giving us examples that simply do not work?
I have built a classical neural network based on IMDB reviews according to the tutorial in one book about AI. 25 000 positive reviews, 25 000 negative reviews. Positive reviews result to "0",...
- 155
0
votes
1
answer
122
views
How do I input multi-channel Numpy array to U-net for semantic segmentation
I had lidar 3D point cloud data from semantckitti. I want to perform Semantic Segmentation on the data using U-Net. I converted the 3d point cloud data into 2D using spherical conversion and saved the ...
1
vote
3
answers
246
views
Does transformers' self-attention mechanism process tokens independently, or entire sequence at a time?
About attention: the Query, Key and Value vectors (before the linear transformations) are just the entire sequence, that is being inputted, or just each token? Chat-GPT nor Youtube didn't give me a ...
-1
votes
1
answer
40
views
1
vote
1
answer
36
views
Can I do incremental learning with different loss function in neural networks?
I have a saved tensorflow neural network model. I was wondering if it's possible to incrementally train the model but with different nt loss function.
- 111
0
votes
1
answer
38
views
Patterns binary classification - model doesn't overfit
I am working on a very basic binary classification problem. For each set of four float numbers $(x,y,z,w)$, I want to check if they fall or not into one category.
I have written a model with 3 dense ...
- 123
0
votes
1
answer
33
views
How to convert my test data in the same dimensionality as my train data
I have trained a VAE with jpg images. My latent space dimension has 768 features and when plotting the latent space it looks like this:
However, when I use the scikit learn tool LDA (Linear ...
- 3
4
votes
2
answers
7k
views
Open-source vocal cloning (speech-to-speech neural style transfer)
I want to program and train a voice cloner, in part to learn about this area of AI, and in part to use as a prototype of audio for testing and getting feedback from early adopters before recording in ...
- 37
2
votes
1
answer
215
views
How does the memory augmented neural network work, and how to make a simple implementation?
How does the memory augmented neural network (MANN) work? How can I make a simple MANN with a vanilla neural network especially without a recurrent network?
- 1,096
0
votes
3
answers
702
views
What is loss function in Neural Networks?
I've been studying NNs with tensorflow and decided to code a simple NN from scratch to get a better idea on hwo they work.
It my understanding that the cost is used in backpropagation, so basically ...
- 13
1
vote
0
answers
380
views
what is tfrs.metrics.FactorizedTopK in tensorflow recommenders
from the official documentation link
In our training data we have positive (user, movie) pairs. To figure out how good our model is, we need to compare the affinity score that the model calculates ...
- 11
4
votes
0
answers
71
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
0
votes
2
answers
6k
views
How "exactly" are AI-accelerator chip ASICs built differently than GPUs as GPU seem to lead for many AI workloads on performance
There is a lot of discussion on google search about AI-custom-accelerators (like Intel's Gaudi) and GPUs.
Almost all of them say generic things like, a) AI Accelerator chip is for specialized AI ...
- 181
1
vote
1
answer
166
views
How do you display a neural network
I'm new to tensorflow and ML but am progressing slowly. I know how to look at the weights and biases but am still trying to figure out if there is an easy way to display a neural network in the ...
- 151
0
votes
1
answer
811
views
Shuffling vs Non-shuffling train/test set yields drastically different results
I am currently working with a very deep NN (200mio. to 350mio. params). My data set is roughly of shape (2mio, 350), i.e. 2mio samples and 350 features. In fact, the features are time series. As input ...
0
votes
0
answers
101
views
Why Is There The Term 1/m In Backpropagation
In backpropagation the gradients are used to update the weights using the formula
$$w = w - \alpha \frac{dL}{dw}$$
and the loss gradient w.r.t. weights is
$$\frac{dL}{dw} = \frac{dL}{dz} \frac{dz}{dw} ...
- 31
3
votes
1
answer
156
views
Custom Tensorflow loss function that disincentivizes all black pixels
I'm training a Tensorflow model that receives an image and segments the image into foreground and background. That is, if the input image is w x h x 3, then the ...
- 33
0
votes
0
answers
59
views
Is the graph considered as overfit?
I have a training dataset of 2000 images and 500 images for validation. I have executed 50 epochs, however I realized that my graph seems to be different as my accuracy is smaller than my loss. I am ...
- 1
1
vote
0
answers
127
views
Hand Landmark Detector Not Converging
I'm currently trying to train a custom model with TensorFlow to detect 17 landmarks/keypoints on each of 2 hands shown in an image (fingertips, first knuckles, bottom knuckles, wrist, and palm), for ...
- 111
2
votes
1
answer
1k
views
Multiple GRU layers to improve a text generation
I am using the model in this colab https://colab.research.google.com/github/tensorflow/text/blob/master/docs/tutorials/text_generation.ipynb#scrollTo=AM2Uma_-yVIq for Shakespeare like text generation.
...
- 121
0
votes
1
answer
165
views
How to handle random order of inputs and get same output?
I am a beginner with DL. I did some tutorials and I know the basics of TensorFlow. But I have a problem understanding how to construct more advanced NNs.
Let's say I have 6 inputs and a list of 500 ...
- 1
0
votes
0
answers
26
views
Training a sequential model that can only evaluate after several hundred cycles
I'm attempting to build a neural network to play the card game, Lost Cities.
A brief overview of the game:
The game involves two players taking turns to play cards on expeditions.
Expeditions incur a ...
1
vote
0
answers
24
views
Neural Network Regression Experiment Going Wrong
I've been trying to get a simple regression experiment going with a neural network and I would like some help interpreting what is going wrong.
My goal is to see what level of regression accuracy I ...
- 111
-1
votes
1
answer
135
views
Exploration for softmax should be binary or continuous softmax?
Maybe it's silly to ask but for random exploration in an RL for choosing discrete action, that in the neural network last layer softmax will be used, what random samples should we provide? binary like ...
2
votes
1
answer
1k
views
Number of parameters in Keras/Tensorflow Dense layers [closed]
I am a bit confused about how the number of parameters are calculated in Dense model for the Kera/Tensorflow.
For example, in the figure below I thought that both the statements were the same, but I ...
- 393
2
votes
1
answer
697
views
Is it possible to use an internal layer's outputs in a loss function?
For a network of the form:
Input(10)
Dense(200)
Dense(100+10)
Dense(20)
Output()
Those +10 outputs are what I want to add to ...
- 141
1
vote
0
answers
146
views
Is it possible to use RGB image with decimal values when feeding training data to CNN?
I am working with four grayscale images of float32 data type to perform regression using Keras. Three images are stacked using np.dstack to form a RGB data-set. The ...
- 11
0
votes
1
answer
96
views
What are possible ways to combat overfitting or improve the test accuracy in my case?
I have asked a question here, and one of the comments suggested that this is a case of severe overfitting. I made a neural network, which uses residual boosting (which is done via a KNN), and I am ...
1
vote
3
answers
170
views
How can I model any structure for a neural network?
Hello I am currently doing research on the effect of altering a neural network's structure. Particularly I am investigating what affect would putting a random DAG (directed acyclic graph) in the ...
- 31
0
votes
1
answer
409
views
Can we use Multiple data as Input in a NN for a single Output?
So I am new to NN and I'm trying to go deep and apply it to my subject. I would like to ask: the input of the NN can be 2 or more values for example-> the measurement of a value, distance, and time?...
- 3
0
votes
1
answer
385
views
Validation Accuracy remains constant while training VGG?
I posted this question on stackoverflow and got downvoted for unmentioned reason, so I'll repost it here, hoping to get some insights
This is the plot
This is the code:
...
- 218
2
votes
1
answer
5k
views
Why is no activation function needed for the output layer of a neural network for regression?
I'm a bit confused about the activation function in the output layer of a neural network trained for regression. In most tutorials, the output layer uses "sigmoid" to bring the results back ...
- 167
6
votes
1
answer
118
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 ...
- 181
2
votes
1
answer
137
views
How to train a neural network with few weights and biases held constant?
I am a beginner in neural networks. I am building a neural network with 3 layers. The input $X$ has 7 features and the output $Y$ is a real number. In the hidden layer, there are two nodes. The bottom ...
- 21
2
votes
0
answers
53
views
If I want to predict two unrelated values given the same sequence of data points, should I have a model with two outputs or two models?
I want to predict two separate y-values (not really logically connected) based on an input sequence of data (values x). Using LSTM cells.
Should I train two models separately or should I just increase ...
- 181
0
votes
0
answers
462
views
Is it possible to transform audio with neural networks to make it sound like 3d sound
so the idea is to feed neural network data like
input: mono audio(extracted from existing 3d audio) output: 3d audio
after training it should convert mono audio to 3d sound
do you think it is possible?...
- 21
0
votes
1
answer
98
views
Extracting information from RNA sequence
I am relatively new to machine learning, and I am trying to use a deep neural network to extract some information from sequences of RNA.
A quick overview of RNA: there is both sequence and structure. ...
- 101
2
votes
2
answers
1k
views
How to recognize sequence of digits in an image
I am learning to program neural networks and others, and I would like to know how I can get the numbers that are in an image, for example, if I pass an image that has 123 written, get with my model ...
- 151
0
votes
1
answer
893
views
Why won't my model train with CTC loss?
I am trying to train an LSTM using CTC loss, but the loss does not decrease when I train it. I have created a minimal example of my issue by creating training data where the network simply has to copy ...
- 101
2
votes
1
answer
145
views
Can TensorFlow, PyTorch, and other mainstream ML frameworks be used for research-grade work in AI?
Many authors of research papers in AI (e.g. arXiv) write their neural networks from the ground-up, using low-level languages like C++ to implement their theories. Can existing open source frameworks ...
- 123
2
votes
1
answer
1k
views
What's the purpose of layers without biases?
I noticed that the TensorFlow library includes a use_bias parameter for the Dense layer, which is set to ...
- 793
2
votes
1
answer
104
views
Evaluate model multiple times in loss function? Is this reinforcement learning?
I am interested in models that exhibit behavior. My goal is a model that survives indefinitely on a two dimensional resource landscape. One dimension represents the location (0 to 1) and the second ...
- 23
2
votes
2
answers
890
views
Extract features with CNN and pass as sequence to RNN
I read an article about captioning videos and I want to use solution number 4 (extract features with a CNN, pass the sequence to a separate RNN) in my own project.
But for me, it seems really strange ...
user40943
0
votes
0
answers
184
views
How GAN generator produce integer RGB colored picture?
For traditional neural networks, I know that we can't constraint the output to be strict integers. My question is what technique does GANs use to produce integer outputs, that can be then converted to ...
- 197
1
vote
0
answers
42
views
Low accuracy during training for text summarization
I am trying to implement an extractive text summarization model. I am using keras and tensorflow. I have used bert sentence embeddings and the embeddings are fed into an LSTM layer and then to a Dense ...
- 41
3
votes
0
answers
258
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 ...
- 31
1
vote
4
answers
420
views
How to improve neural network training against a large data set of points with varying magnitude
I am currently using TensorFlow and have simply been trying to train a neural network directly against a large continuous data set, e.g. $y = [0.014, 1.545, 10.232, 0.948, ...]$ corresponding to ...
- 61