Questions tagged [deep-learning]

For questions related to deep learning, which refers to a subset of machine learning methods based on artificial neural networks (ANNs) with multiple hidden layers. The adjective deep thus refers to the number of layers of the ANNs. The expression deep learning was apparently introduced (although not in the context of machine learning or ANNs) in 1986 by Rina Dechter in the paper "Learning while searching in constraint-satisfaction-problems".

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

Numbers to image regression

I would like to create a machine learnig framework that could predict the 3D heat distribution of a room(of size 120x120x120) , given multiple parameters(position of the heater, orientation, power of ...
0
votes
2answers
38 views

LSTM network doesn't converge, what should be changed? [on hold]

I'm testing out TensorFlow LSTM layer text generation task, not classification task; but something is wrong with my code, it doesn't converge. What changes should be done? Source code: ...
1
vote
0answers
22 views

How to get same accuracy with identical models in Keras and Tensorflow?

As we all know Keras backend uses Tensorflow and so it should give out same kind of results when we provide same parameters, hyper-parameters, weights and biases initialisation at each layer, but ...
3
votes
1answer
23 views

Query on another perspective on Deep Learning

At least at some level, maybe not end-to-end always, but Deep Learning always learns a function, essentially a mapping from a Domain to a Range. The Domain and Range, at least in most cases, would be ...
1
vote
1answer
21 views

DQN regarding fitting off actions

While studying DQN, I rarely if ever see an explanation of what to fit off actions to. Meaning, if the highest valued action of 3 choices if the first, when training, what do we do with the other two ...
2
votes
0answers
11 views

Tensorflow and Keras model having same parameters, hyperparameters, weight and bias initialization give different accuracy?

I have made sure that layers,parameters, hyperparameters,kernel_initialization, bias_initialization, seed and dataset are all equal. But still the output for both the models are different. ...
0
votes
1answer
24 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
0answers
26 views

Neural Network training on one example to try overfitting leads to strange predictions

tldr; if I train the network on 1 training example, the outcome sometimes makes no sense at all, sometimes is as expected. If I train it on more examples and higher iterations, the network, which ...
3
votes
1answer
22 views

Image classification with an associated matrix

I have a dataset of images with 9 different classes. However, there are different categories with the same type of associated image and only can be differentiated with an associated matrix in my ...
1
vote
0answers
11 views

CBIR Evaluation on contextually different data

How good would a CBIR system trained on a dataset, for example, DELF, trained on the Google Landmarks dataset, perform when evaluated on a contextually different dataset such as the WANG or the COREL ...
2
votes
2answers
39 views

Can ML be used to curve fit data based on dataset of example fits?

Say I have x,y data connected by a function with some additional parameters (a,b,c): $$ y = f(x ; a, b, c) $$ Now given a set of data points (x and y) I want to determine a,b,c. If I know the model ...
1
vote
1answer
27 views

How well can ConvNET distinguish an object from its class?

ConvNET can easily predict class of an object in an image. My question is, can ConvNET distinguish Pisa Tower from other buildings or Hagia Sophia from other mosquoes easily? If it can, how many ...
0
votes
0answers
12 views

Why do both sin and cos have been used in positional encoding in Transformer model?

The Transformer model proposed in "Attention Is All You Need" uses sinusoid functions to do positional encoding. I wonder why do both sin and cos been involved in? And why do need to separate the odd ...
-1
votes
1answer
31 views

How to calculate the false positives and negatives?

I have a huge amount of data and I want to calculate my false positive and false negative. Is there a software that can help me determine it?
1
vote
0answers
27 views

why the sigmoid function will be 1 and 0 if we use a fully connected layer that produce a big enough positive(res negative )output

HI I am using a fully connected network that uses sigmoid if we feed a a big enough weights the sigmoid function will finally become 1 or 0 , is there any solution to avoid this ? and will this lead ...
0
votes
0answers
9 views

Matterport MRCNN and multiclass classification

I want to create a model which solve a multiclass classification problem. The main concept is: every picture contain only one object the background is very simple all object is coming from the same ...
0
votes
0answers
6 views

Object detector always predict high confidence bounding box after dataset augmentation

I am using the Object Detection API to train a MobilenetV2-SSD object detector with just one class. I started from the sample pipeline tuned for the COCO dataset. During the first training I could ...
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: ...
3
votes
1answer
31 views

Reinforcement learning with hints or reference model

In Reinforcement Learning, when I train a model, it comes up with its own set of solutions. For example, if I am training a robot to walk, it will come up with its own walking gait, such as this Deep ...
0
votes
0answers
12 views

Invalid moves in Deep Reinforcement Learning for games [duplicate]

I've been working on a bot for a game involving dice throws and chance. The architecture involved is similar to AlphaZero in the that it has Convolutions and MCTS. According to the current state ...
0
votes
0answers
10 views

Is there any reason to believe a ml pipeline that works on dataset A will work on dataset B where both have similar meta features?

I’m working on generating an automl pipeline(a combination of data cleaning and transformation algorithms applied to a dataset then generate a model) that works on a new dataset by looking for past ...
3
votes
1answer
68 views

How is the gradient of the loss function in DQN derived?

In the original DQN paper, page 1, the loss function of the DQN is $$ L_{i}(\theta_{i}) = \mathbb{E}_{(s,a,r,s') \sim U(D)} [(r+\gamma \max_{a'} Q(s',a',\theta_{i}^{-}) - Q(s,a;\theta_{i}))^2] $$ ...
3
votes
1answer
48 views

Is it useful to eliminate the less relevant filters from a trained CNN?

Imagine I have a tensorflow CNN model with good accuracy but maybe too many filters: Is there a way to determine which filters have more impact in output? I think it should be possible. At least, if ...
0
votes
1answer
43 views

Should the biases be zero or randomly initialised?

I'm initialising DNN of shape [2 inputs, 2 hiddens, 1 output] with these weights and biases: ...
-1
votes
2answers
153 views

Should I use the Threadripper 2920X or Ryzen 7 3700X?

Update 2 The OS I'm using is Windows 10, since we have WSL, I also use Ubuntu to run the code. The code is written in Python. I know there are thousands of factors which affect the final performance ...
0
votes
0answers
23 views

How to update Loss Function parameter after compilation

I used following custom loss function. ...
1
vote
1answer
28 views

What does an oscillating validation error curve represent?

I have been training my CNN for a bit now and, while both the training loss and the training error curves are going down during training, both my validation loss and my validations error curves are ...
2
votes
0answers
34 views

When to use RMSE as opposed to MSE and vice versa?

I understand that RMSE is just the square root of MSE. Generally, as far as I have seen, people seem to use MSE as a loss function and RMSE for evaluation purposes, since it exactly gives you the ...
1
vote
2answers
25 views

How does one create a non-classifying CNN in order to gain information from images?

How do I program a neural network such that, when an image is inputted, the output is a numerical value that is not the probability of the image being a certain class? In other words, a CNN that doesn'...
1
vote
1answer
30 views

Can ConvLSTMs outuput images?

I am working on an image to image regression task which requires me to develop a deep learning model that takes in a sequence of 5 images and return another image. The sequence of 5 images and the ...
2
votes
0answers
25 views

Image to image regression in tensorflow

I am working on an image to image regression task which requires me to develop a deep learning model that takes in a sequence of 5 images and return another image. The sequence of 5 images and the ...
1
vote
1answer
8 views

What should load_mask() return if an image doesn't have any objects? (Mask RCNN)

I want to use Mask RCNN to do image segmentation. I need to override the load_mask function for the dataset class. I know this function should return mask tensors and class ids of objects in an image. ...
2
votes
0answers
36 views

Feasibility of using machine learning to obtain self-consistent solutions

I am a physicist and I don't have much background on machine learning or deep learning except taking a couple of courses on statistics. In physics, we often simulate a model by means of two-way ...
2
votes
1answer
55 views

Using True Positive as a Cost Function

I wanted to use True Positive (and True Negative) in my cost function to make to modify the ROC shape of my classifier. Someone told me and I read that it is not differentiable and therefore not ...
4
votes
2answers
131 views

What does the symbol $\mathbb E$ mean in these equations?

I came across some papers that use $\mathbb E$ in equations, in particular, this paper: https://arxiv.org/pdf/1511.06581.pdf. Here is some equations from the paper that uses it: $Q^\pi \left(s,a \...
2
votes
1answer
43 views

Video engagement analysis with deep learning

I am trying to rank video scenes/frames based on how appealing they are for a viewer. Basically, how "interesting" or "attractive" a scene inside a video can be for a viewer. My final goal is to ...
-1
votes
1answer
114 views

Can a neural net learn to read?

I am a student of last year of computer engineering and lately I have been very interested in AI. Fields such as ML and DL seem very disruptive to me. A few months ago I saw an interview of Bill ...
2
votes
2answers
36 views

Dealing with empty frames in MRI images

I started working on the application of deep learning in medical imaging recently. While dealing with MRI images in the BraTS dataset, I observe that first and last few frames are always completely ...
1
vote
0answers
42 views

Torch CNN not training

I am completely new to CNN's, and I do not quite know how to design or use them efficiently. That being said, I am attempting to build a CNN that learns to play Pac-man with reinforcement learning. I ...
0
votes
1answer
15 views

Solution to classify product names

I have a bunch of training data for classifying product names, around 30,000 samples. The task is to classify these product names into types of product, around 100 classes (single words). For example:...
1
vote
1answer
38 views

TensorFlow estimator DNNClassifier fails to fit simple data

The ready-to-use DNNClassifier in tf.estimator seems not able to fit these data: ...
4
votes
0answers
21 views

Extending FaceNet’s triplet loss to object recognition

FaceNet uses a novel loss metric (triplet loss) to train a model to output embeddings (128-D from the paper) such that any two faces of the same identity will have a small Euclidean distance, and such ...
2
votes
1answer
33 views

How to generate the original image from feature set?

We all know that using CNN, or even simpler functions, like CLD or EHD, we can generate a set of features out of images. Is there any ways or approaches that given a set of features, we can somehow ...
2
votes
1answer
43 views

Is normalizing the data a way to improve generalization?

There are many known ways to overcome overfitting or make a model generalize better to unseen data. Here I would like to ask if normalizing/standardizing/similiraizing the train and test data is a ...
0
votes
0answers
11 views

Video multi context or action annotation / labeling

I've a lot of collected driving data, including video data streams. In order to filter or use them for DNN training, the video files must be annotated / labeled. In contrast to object detection or ...
0
votes
0answers
19 views

Suggestion on How to Push SARS to Memory Buffer of Losing RL Agent in Adversarial Learning

I am trying to implement my first RL program where there are multiple agents, rather than just one. The environment I am using is the connect four game, which is turn-based. In DQ-Learning, an agent ...
0
votes
0answers
15 views

Suggestions for Deep Learning for regression on huge 3D volumes

I have a dataset of 3D images (volumes) with dimensions 400x250x400. For each input image I have an output of the same dimensions. I would like to train a machine learning (or deep learning) model on ...
2
votes
2answers
30 views

Conferences for Human Activity Recognition

What are some conferences for publishing papers on Deep Learning for Human Activity recognition? Do any of the major conferences have specific tracks for Human Activity Recognition?
1
vote
1answer
148 views

Online Learning for Neural Networks

There seems to be a lot of literature and research on the problems of stochastic gradient descent and catastrophic forgetting, but I can't find much on solutions to perform online learning with neural ...
2
votes
1answer
54 views

Aesthetics analysis with deep learning

I'm trying to score video scenes in terms of aesthetics and cinematography features. Basically, how "interesting" a scene or video frame can be for a viewer. Simpler, how attractive a scene is. My ...