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
1
vote
0answers
41 views

Which model should I choose to maximise reward of having chosen two numbers from a list?

I am looking for a technique to train a machine learning model to choose two items from a list. So, given a list $x=[x_1, x_2, x_3, x_4, \dots, x_n]$, the model needs to choose two elements $(x_i, ...
1
vote
1answer
24 views

How to use convolution neural network in Deep-Q?

I currently have a grid of pixels 20x20. Each pixel can be red green blue or black. So I have one hot-encoded the pixels giving a 20x20x4 array for each screen. For my Deep-Q Network, I have ...
1
vote
0answers
10 views

Convolutional Feature Encoding Methods in DCNN

In Computer Vision, feature encoding methods are used on pre-trained DCNN to increase the feature robustness to certain conditions such as viewpoint/appearance variations ref. I was just wondering if ...
1
vote
0answers
13 views

How positional encoding works?

In transformer model; to incorporate positional information of texts the researchers have added a positional encoding to the model. How is positional encoding works? How positional encoding system ...
1
vote
0answers
17 views

Tensorflow based implementation of Text classification with any variation of BERT(ALBERT/XLNET)

Do you have any reference you can point me to for doing Text classification using any variation of BERT(albert or XLnet) with a TF implementation. I am not sure how to deploy torch based models, so ...
1
vote
1answer
49 views

Why do we regularize the variational autoencoder with a normal distribution?

When we define the loss function of a variational autoencoder (VAE), we add the Kullback-Leibler divergence between the sample taken according to a normal distribution of parameters: $$ N(\mu,\sigma)...
1
vote
0answers
18 views

Train an AI to infer accurate mathematical calculations by simply “looking” at images of shapes/objects

I’d like to build a model that has an understanding of geometry, where it can be applied to question and answering system. Specifically, it would be nice if it could determine the volume of an object ...
1
vote
0answers
24 views

What are the pros and cons of the common activation functions?

I have heard that sigmoid activation functions should not be used on neural networks with many hidden layers as the gradients tend to vanish in deep networks. When should each of the common ...
1
vote
1answer
29 views

Why is the sample size of stochastic gradient descent a power of 2?

I watched in the video lecture of cs224: Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 2 – Word Vectors and Word Senses. They take the sample size of the window to be $2^5 = 32$ or $...
0
votes
0answers
41 views

Intuition behind single-shot object detection

Is there a good way to understand how single-shot object detection works? The most basic way to do detection is use a sliding-window detector and look at the output of the NN to detect if a class is ...
1
vote
0answers
32 views

How can I normalize gamestates in order to use with a machine learning library?

I have currently collected 150000 gamestates from playing a Monte Carlo Tree Search AI player against a basic rule based AI at the game of Castle. The information captured represents the information ...
4
votes
1answer
841 views

What is the purpose of the batch size in neural networks?

Why is a batch size needed to update the weights of a neural network? According to that Youtube Video from 3B1B, the weights are updated by calculating the error between expectation and outcome of ...
2
votes
0answers
58 views

Why gradients are so small in deep learning?

The learning rate in my model is 0.00001 and the gradients of the model is within the distribution of [-0.0001, 0.0001]. Is it ...
1
vote
0answers
17 views

What's the best method to predict/generate signal from one sensor (source) to signal from another another (target)?

I was wondering what is the best method out there to find relationship between two 1D signals so that I can predict/generate one (source) from the other (target). For example, let's say that in ...
2
votes
0answers
38 views

Suitable deep learning algorithms for spatial / geometric data

I have a task of classifying spatial data from a geographic information system. More precisely, I need a way to filter out unnecessary line segments from the CAD system before loading into the GIS (...
1
vote
1answer
34 views

Is it legal to construct a public image database (for deep learning) with images from the internet? [closed]

I am trying to put together a public agricultural image database of corn and soybeans, to train convolutional neural networks. The main method of image collection will be through taking pictures of ...
1
vote
0answers
153 views

How can I deploy a Keras machine translation model on Flask or django [closed]

I want to deploy a machine translation system implemented in Keras on Flask. In which format do I have to save my model for flask? Is there a tutorial that shows how to deploy a Keras model on Flask?...
0
votes
1answer
28 views

Is it possible to use deeplearning with spark (with a distributed databases as HDFS or Cassandra)?

If it is possible, will it be really useful or the model will end up converging very early(with a typical optimum learning rate) ? Any content on this topic will be helpful for me.
0
votes
1answer
73 views

Why is my loss (binary cross entropy) converging on ~0.6? (Task: Natural Language Inference)

I’m trying to debug my neural network (BERT fine-tuning) trained for natural language inference with binary classification of either entailment or contradiction. I've trained it for 80 epochs and its ...
4
votes
1answer
99 views

Many of the best probabilistic models represent probability distributions only implicitly

I am currently studying Deep Learning by Goodfellow, Bengio, and Courville. In chapter 5.1.2 The Performance Measure, P, the authors say the following: The choice of performance measure may seem ...
3
votes
3answers
495 views

What are the differences between transfer learning and meta learning?

What are the differences between meta-learning and transfer learning? I have read 2 articles on Quora and TowardDataScience. Meta learning is a part of machine learning theory in which some ...
2
votes
1answer
22 views

deep learning with kfold cross validation with epochs

I am new into neural networks, I want to use K-fold cross-validation to train my neural network. I want to use 5 folds 50 epochs and a batch size of 64 I found a function in scikit for k-fold cross ...
1
vote
3answers
209 views

What kind of optimizer is suggested to use for binary classification of similar images?

I have spent some time searching Google and wasn't able to find out what kind of optimization algorithm is best for binary classification when images are similar to one another. I'd like to read ...
2
votes
2answers
67 views

How can I perform lossless compression of images so that they can be stored to train a CNN?

I have a set of images, which are quite large in size (1000x1000), and as such do not easily fit into memory. I'd like to compress these images, such that little information is missing. I am looking ...
1
vote
0answers
12 views

Drone Deployment Platform for Neural Networks

Good day everyone, I would just like to ask if anyone part of a lab or company doing research on aerial robotics has any suggestions of a good platform for deploying computer vision algorithms for ...
2
votes
0answers
38 views

How does adding noise to the action in DDPG help in learning?

I can't understand how playing with the action generated by the actor network in DDPG by adding the noise term helps in exploration.
2
votes
2answers
53 views

Are connections genes in a genome ever deleted or just disabled?

When a new node is added, the previous connection is disabled and not removed. Is there any situation in which a connection gene is removed? For example, in the above diagram connection gene with ...
1
vote
2answers
45 views

Traffic Sign Detection and Recognition

I'm working on a project for my college to recognize traffic sign from a picture I searched a lot but can't find the best method to do it can someone recommend me a paper, article or even GitHub link ...
1
vote
0answers
22 views

How is the receptive field of a CNN affected by transposed convolution?

When computing receptive field recursively through a CNN, does a transposed convolution affect the receptive field the same way that a convolution does if the kernel and stride is the same?
0
votes
0answers
14 views

Computing latent representation for multi-domain regression/classification

Suppose I have a dataset with (X, Y) training samples where X is a 1 dimension, and Y is also 1 dimension. Example: if this is a housing price dataset, X would be an area in square feet, and Y would ...
0
votes
0answers
10 views

How to handle multiscale time series for DNN?

I have a time-series signal with data sampled every minute. I've made different scales of the original signal like 30 minutes, 1 hour and ... . Now because the lengths of these signals are different I'...
1
vote
0answers
43 views

Can neural network be trained to solve this problem?

I'm working on a problem that given a dataset; where each train example is a binary matrix $X_i$ with dimension $(N_i,D_i)$ (think a training example is a feature matrix) each entry is either 1 or 0. ...
2
votes
0answers
44 views

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling?

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling? If not, why do they perform as well as networks which use max-pooling?
1
vote
0answers
8 views

Standardize images using ImageDataGenerator in keras

I was trying to normalize my input data images for feeding to my convolutional neural network and wanted to use standardize my input data. I referred to this article: https://stackoverflow.com/...
1
vote
1answer
29 views

How to get top 5 movies recommendations from Auto-Encoder

I have trained a model using Auto-encoder on movielens dataset. Below is how i trained the model. ...
2
votes
1answer
61 views

How to detect vanishing gradients?

Edit: I've reworked my question to generalize better and be more on-topic, and be mostly software implementation agnostic. Can vanishing gradients be detected by the change in distribution (or lack ...
1
vote
1answer
36 views

How to estimate the error during training in deep reinforcement learning

How do I calculate the error during the training phase for deep reinforcement learning models? Deep reinforcement learning is not supervised learning as far as I know. So how can the model know ...
1
vote
0answers
28 views

How to reduce fluctuation of a neural network?

I've modeled an AlexNet neural network, with 50 epochs and a batch size of 64. I used a stochastic gradient descent optimizer with a learning rate of 0.01. I attached the train and validation loss and ...
0
votes
0answers
14 views

augmentation, cross-validation, test evaluation

I have, say, a (balanced) data-set with 2k images for binary classification. What I have done is that randomly divided the data-set into 5 folds; copy-pasted all 5-fold data-set to have 5 exact ...
0
votes
0answers
20 views

Steps to train and re-train a good model

I'm still a bit new to deep learning. What I'm still struggling, is what is the best practice in re-training a good model over time? I've trained a deep model for my binary classification problem (...
-1
votes
1answer
51 views

can i use machine or deep learning in windows instead of Ubuntu? [closed]

I'm new to Machine Learning and want to start to learn it .. Does windows environment be good or i must use Ubuntu
1
vote
0answers
13 views

Details on body measurements prediction

if someone want to do mobile app for body measurements prediction, please what are the necessary things to start with. I need details explanation on this.
1
vote
0answers
17 views

How to encode board before input into the neural net?

Currently I'm working on an educational project (implementation of AlphaZero approach to different types of board games). My biggest concern at the moment is how to encode board before input into the ...
1
vote
0answers
19 views

Pytorch deep learning models and tabular data representation

I have quite a naive question regarding Pytorch deep learning models and tabular data representation. So, assume I have a dictionary of tables. Each table has some number of columns: categorical and ...
1
vote
0answers
23 views

Noise Cancellation on live audio stream

I want to build an application which takes a live audio from source (mic) and filtering the noise (unwanted sounds like chattering, traffic noises) and fetch into an application for further processing....
4
votes
1answer
102 views

Is there a reason to use TensorFlow over PyTorch for research purposes?

I've been using PyTorch to do research for a while and it seems to be quite easy to implement new things with. Also, it is easy to learn and I didn't have any problem with following other researchers ...
2
votes
1answer
51 views

Should I prefer the model with the lowest validation loss or the highest validation accuracy to deploy?

I trained a ResNet20 on Cifar10 and obtained the following learning curves. From the figures, I see at epoch 52, my validation loss is 0.323 (the lowest), and my validation accuracy is 89.7%. On the ...
1
vote
1answer
33 views

Hand-Signs Recognition using Deep Learning Convolutional Neural Networks

I am developing a CNN model to recognize 24 hand-signs of American Sign Language. I have 2500 Images/hand-sign. The data split is: Training = 1250 Images/hand-sign Validation = 625 Images/hand-sign ...
0
votes
1answer
25 views

Choosing Data Augmentation smartly for different application

I'm trying to understand the role of data augmentation and how it can affect the performance/accuracy of a deep model. My target application is fire detection (on video frames), with almost 15K ...
2
votes
0answers
46 views

External GPU for Mac

I'd like to buy an eGPU for my MaxBook Pro to use for simple deep learning tasks. My setup is: ...

1 2 3
4
5
23