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
9 views

Emotional Speech Synthesis

We are a team of computer science our graduation project about EmotionalSpeech Synthesis. We've found valuable information like research papers and WaveNet, Tacotron. A website (https://www.voicery....
2
votes
1answer
19 views

Doubt in Deep-Q learning with sparse rewards

I am working on a deep reinforcement learning problem, when I got stuck at the following questions. They are rather general and not specific to my specific problem. The solution uses a sparse reward ...
0
votes
0answers
8 views

Which metrics of COCO API are suitable for object detection

These days I train a person detector and I use COCO API to evaluate my model. It uses Recall and Precision to evaluate a detection task. It's output is something like this: ...
2
votes
1answer
29 views

What are sim2sim, sim2real and real2real?

Recently, I always hear about the terms sim2sim, sim2real and real2real. Will anyone explain the meaning/motivation of these terms (in DL/RL research community)? What are the challenges in this ...
1
vote
1answer
27 views

Why is image classification tasks are dominated by minimizing cost function instead of maximizing ones?

I was watching a video of policy gradient by Andrej Karpathy at 10:00 there shows an equation for supervised learning for image classification. $max\sum _{i}log \:p(y_i|x_i)$ I have worked with ...
2
votes
0answers
22 views

Are there methods that allow deep networks to learn object categorization in a self-supervised way?

When training a deep network to learn object classification from a set like ImageNet, we minimize the cross entropy between the ground truth and the predicted categories. This is done in a supervised ...
1
vote
0answers
18 views

Why hasn't deep learning been used for word level alignment?

I've been exploring word-level alignments tools such as MGIZA and it seems to me that there hasn't been any new tool for this problem. Are neural networks not suitable to solve this problem or simply ...
0
votes
1answer
23 views

Is this learning rate schedule increasing the learning rate?

I was reading a PyTorch code then I saw this learning rate scheduler: ...
0
votes
3answers
106 views

Is machine learning required for deep learning?

The answers to this Quora question say it's OK to ignore machine learning and start right away with deep learning. Is machine learning required or is useful for understanding (theoretically and ...
1
vote
0answers
8 views

Can someone please explain the basics of a procedural reason system?

I’m a complete beginner so any help is appreciated
1
vote
2answers
50 views

Can multiple activation functions be replaced with a single activation function?

I'm just started to learn deep learning and I have a question about this neural network: I think $h_1$, $h_j$ and $h_n$ are perceptrons. So, if they are perceptrons, all of them will have an ...
2
votes
0answers
11 views

How to choose the suitable Neural Network Architecture for Regression Tasks

so I'm working on a Project where I want to predict the Vehicle Position from the Vehicle Data like speed, acceleration etc.. now the data that I have comes also with a timestamp for each sample ( I ...
0
votes
0answers
52 views

How to develop face recongiton program using CNN to obtain more than 95% accuracy? [closed]

I want to develop face recognition program using convolutional neural network. Can some one tell me steps to follow to do the same? I am new to deep learning. I want to develop it on windows using ...
0
votes
0answers
7 views

How does keras `train_on_batch` return value work?

From the doc, train_on_batch() will return a scalar representing the loss and the metric. I want to know whether the loss/metric is evaluated before the weight is ...
-1
votes
0answers
36 views

who built the great pyramids in Egypt? [closed]

There is some disagreement on the age of the pyramids of egypt. How old are the pyramids
1
vote
1answer
25 views

How to use a deep learning network on new data-set?

I am trying to use a network for classification. This network works very well on the author's example data, but doesn't work on new data. Currently, I am using the popular EEG Motor Movement/Imagery ...
1
vote
1answer
31 views

Can A.I/Deep Learning use one image as content for another image?

Is it possible for A.I to redraw an image in a new context? More specifically, suppose I take a photo of a notebook. I get the angle, lighting and perspective perfect. Now I copy an image I found ...
4
votes
2answers
61 views

What is the benefit of using identity mapping layers in deep neural networks like ResNet?

As I understand Resnet has some identity mapping layers that their task is to create the output as the same as the input of the layer. the resnet solved the problem of accuracy degrading. But what is ...
0
votes
0answers
12 views

Choosing best combinations from all possible combination expressions based few variables, unary operators, binary operators

I have a few financial variables of a stock universe like OHLC prices, volume, and other fundamentals with varying time-frequency. Using this set I'm creating an expression that gives the weights to ...
32
votes
20answers
10k views

Can digital computers understand infinity?

As a human being, we can think infinity. In principle, if we have enough resources (time etc.), we can count infinitely many things (including abstract, like numbers, or real). For example, at least, ...
1
vote
1answer
40 views

“Outside-in” versus “Inside-out” machine learning

A little background... I’ve been on-and-off learning about data science for around a year or so, however, I started thinking about artificial intelligence a few years ago. I have a cursory ...
1
vote
0answers
7 views

Looking or the simplest framework to train keypoint detector

I currently use an object detector to detect an object and specific parts of it (a crop and its stem). Such detector is not the best choice for detecting parts that could be represented by a point (...
0
votes
0answers
22 views

How to calculate covariance matrix of the mini-batch in the k-th layer using Python?

I am a beginner in Python. I want to calculate the covariance matrix of a mini-batch in a given hidden layer.
1
vote
2answers
42 views

Why is embedding important in NLP, and how does autoencoder work?

People say embedding is necessary in NLP because if using just the word indices, the efficiency is not high as similar words are supposed to be related to each other. However, I still don't truly get ...
5
votes
1answer
37 views

Why do very deep non resnet architectures perform worse compared to shallower ones for the same iteration? Shouldn't they just train slower?

My understanding of the vanishing gradient problem in deep networks is that as backprop progresses through the layers the gradients become small, and thus training progresses slower. I'm having a hard ...
3
votes
1answer
43 views

Is it possible to do K-nearest-neighbours before training DNN

The following X-shape alternated pattern can be separated quite well and super fast by K-nearest Neighbour algorithm (go to http://ml-playground.com to test it): However, DNN seems to face great ...
0
votes
0answers
7 views

Fusing label distribution and on-hot encoded labels

A while ago I came across a paper for image classification that utilized both label distribution and one-hot encoded labels to classify images. An image has a label distribution for all classes (4 ...
0
votes
0answers
9 views

What is best dataset for person reidentification?

There are many datasets for person reidentification. I want to train a robust person re-identification neural network. Therefore I want to ask about best person re-identification dataset.
9
votes
0answers
60 views

Will parameter sweeping on one split of data followed by cross validation discover the right hyperparameters?

Let's call our dataset splits train/test/evaluate. We're in a situation where we require months of data so we prefer to use the evaluation dataset as infrequently as possible to avoid polluting our ...
3
votes
0answers
22 views

Vector normalization by a neural network

I'm wondering if there is a NN that can achieve the following task: Output a unit vector that is parallel to the input vector. i.e., input a vector $\mathbf{v}\in\mathbb{R}^d$, output $\mathbf{v}/\|\...
11
votes
1answer
179 views

What are all the different kinds of neural networks used for?

I found the following neural network cheat sheet (Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data). What are all these different kinds of neural networks used ...
0
votes
0answers
7 views

How is Average Recall (AR) calculated for an object detection model?

After looking around the internet (including this paper, I cannot seem to find a satisfactory explanation of the Average Recall (AR) metric. On the COCO website, it describes AR as: "the maximum ...
0
votes
0answers
17 views

Better versions of LSTM

I know recurrent neural networks for example LSTM is one of them. After LSTM different variants of LSTM have come for example GRU. I don't know about newer RNN like LSTM and GRU, so I decided to ask ...
1
vote
0answers
31 views

Is there a GAN that can be used for sequence prediction?

I want to use a GAN for sequence prediction, in a similar way that we use RNNs for sequence prediction. I want to test its performance in comparison with RNNs. Is there a GAN that can be used for ...
0
votes
0answers
9 views

what is the best dataset (or combination of datasets) for training a person detector?

I want to train a person detector for MOTChallenge dataset, but I want to avoid using the dataset as training set for my detector. Therefore, I want to use another dataset or combination of several ...
0
votes
0answers
13 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
54 views

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

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
24 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
30 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
28 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 ...
1
vote
1answer
29 views

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

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
29 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
12 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
41 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
30 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
15 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
36 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
30 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 ...