Questions tagged [deep-learning]

a new area of Machine Learning research concerned with the technologies used for learning hierarchical representations of data, mainly done with deep neural networks (i.e. networks with two or more hidden layers), but also with some sort of Probabilistic Graphical Models.

Filter by
Sorted by
Tagged with
1
vote
2answers
95 views

Homemade deep learning library: numerical issue with relu activation

For the sake of learning the finer details of a deep learning neural network, I have coded my own library with everything (optimizer, layers, activations, cost function) homemade. It seems to work ...
3
votes
1answer
76 views

Setting “missing” distance values to zero when training a neural network

Not sure if missing values is the right name to use here. I want to train a DNN on data given by a sensor. The sensor gives the (x,y) coordinates of the founded objects. The sensor can keep track of ...
1
vote
1answer
139 views

Forward and backward process in pyTorch

When I write a network, do I have to write the whole forward property in nn.Module.forward()? I mean if I do some operations outside the net, does grad correctly ...
5
votes
1answer
6k views

What is the input size of Alex net

In the paper ImageNet Classification with Deep Convolutional Neural Networks, the size of input image is 224x224. The following figure shows the input size. From caffe, deploy.prototxt file from the ...
2
votes
1answer
115 views

Is color information only extracted in the first input layer of a convolutional neural network?

In a convolutional neural network (CNN), since the RGB values get multiplied in the first convolutional layer, does this mean that color is essentially only extracted in the very first layer? ...
6
votes
2answers
780 views

In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?

The example below is taken from the lectures in deeplearning.ai shows that the result is the sum of the element-by-element product (or "element-wise multiplication". The red numbers represent the ...
1
vote
0answers
38 views

How do I learn encoding of a text that is encoded at character level? [closed]

Encoded text at character level: ...
1
vote
0answers
133 views

Is it possible to have variable window size for Continuous Bag of Words method of training word embeddings?

All the literature I've seen so far in the CBOW model uses a fixed window size, ie window size of 2. Is it possible to have a variable window size? For example, one set will have 8 words for input ...
1
vote
1answer
1k views

building a prediction model using CNN

I have an input array X, which is of the shape (38000,32,1); the output array Y is of (38000,1), the element of Y can be ...
0
votes
1answer
420 views

What is the minimum/suggested sequence length for training an LSTM? [closed]

My dataset consists of short videos of 4/5 time-steps each (frames), and the problem is classifying this video (multi-label classification). The idea is to use an LSTM but I'm wondering if the ...
0
votes
1answer
47 views

What are temporal and local data? [closed]

Based on the question, what are they and what are their differences? I've seen a lot those terms but cannot find an appropriate answer.
1
vote
0answers
18 views

How are dynamic memory networks employed in sequence to sequence modelling

Dynamic Memory networks are described here . I understand what is going on for question answering task but when it comes to sequence to sequence modeling, they describe it in 4th paragraph of 2.4 ...
9
votes
2answers
410 views

what machine/deep learning/ nlp techniques are used to classify a given words as name, mobile number, address, email, state, county, city etc

I am trying to generate an intelligent model which can scan a set of words or strings and classify them as names, mobile numbers, addresses, cities, states, countries and other entities using machine ...
4
votes
2answers
733 views

How can a GRU perform as well as an LSTM?

I think I understand both types of units in terms of just the math. What I don't understand is, how is it possible in practice for a GRU to perform as well as or better than an LSTM (which is what ...
0
votes
1answer
650 views

Text analysis - classification, parsing

Excuse if this has been answered before. I need to extract features and parse from a piece of text and run some analysis. For e.g. "Plot the past 5-year sales of Apple" should give me the following ...
-1
votes
1answer
93 views

Alert generation on unseen data using deep learning

I am new in neural network and deep learning, trying to create a deep learning model to classify images. While reading blogs and videos, a question comes in my mind and not able to find the correct ...
0
votes
2answers
269 views

Is it possible to design a deep CNN model on a small size image dataset

I have started a project of classifying a dataset using deep learning. I have tried transfer learning on pretrained models. Now, I want to design a CNN model which can do this work of classification ...
1
vote
0answers
84 views

Looking for a ml algorithm to predict a path based on millions of data

I have a dataset with following data format: 3 -> a -> b -> c -> d -> ikd a -> c -> 3 -> dk -> 2 -> l2i each row represents a path ...
1
vote
1answer
3k views

Get the probabilities of Tensorflow

Hi I am studying tensorflow for cifar-10 image classification using the code here
1
vote
0answers
175 views

Unevenly stretched sequences with LSTM/GRU

I am looking for a right NN architecture(probably, based on LSTM/GRU) for the classification problem I faced. I have an alphabet of events {A, B, C, D, ..., N} and sequences of these events for each ...
2
votes
1answer
1k views

Interpreting confusion matrix and validation results in convolutional networks

I need some help in the assessment of the training results of a convolutional neural network. Here is my setup: Architecture: InceptionV3 Pre-trained InceptionV3 with weights from image net ...
4
votes
2answers
2k views

What is dilated pooling and how it works mathematically?

While I understand the concept of dilated convolution as there are lot of papers explaining about it, I have heard less about dilated pooling. Can someone explain what it is? What is the internal ...
1
vote
0answers
42 views

Understand the shape of this Convolutional Neural Network

I'm trying to implement what is explained in a paper on audio signal processing. The guys who wrote this paper tried a Convolutional Neural Network and here is how they explain it : "The CNN are ...
10
votes
2answers
12k views

How to maximize recall?

I'm a little bit new to machine learning. I am using a neural network to classify images. There are two possible classes. I am using Sigmoid activation at the last ...
1
vote
0answers
60 views

How to get intuitive understanding which deep learning architecture suits for my problem

I'm working on a research problem where I need to perform classification for coarse prediction in a feature space and then fine grained regression for getting more precise values. I know that this way ...
5
votes
4answers
2k views

How to fix these vanishing gradients?

I am trying to train a deep network for twitter sentiment classification. It consists of an embedding layer (word2vec), an RNN (GRU) layer, followed by 2 conv layers, followed by 2 dense layers. Using ...
3
votes
2answers
2k views

Why do we have multiple neurons in the output layer of a neural network?

Why do we have two neurons in the output layer? What does each neuron mean? If our classifier is a binary classifier, will we have only one neuron in the output layer? Here is a picture of the ...
0
votes
1answer
114 views

Learning Rate based on error of the network

I am not an expert and do not have theoretical justification for that, but it seems to me that the smaller network error is, the smaller learning rate should be. Is there an algorithm to dynamically ...
2
votes
1answer
253 views

How does a Recommender System recommend movies to a New User?

Consider a New user which has never rated any movie on the Website or the System has never seen the user. How does the System recommend Movies to the User and based on what ? How will we evaluate ...
2
votes
1answer
1k views

One sided label smoothing in GANs

How does one-sided label smoothing make the discriminator more robust by reducing the confidence in correct class?
0
votes
1answer
464 views

Multimodal distribution and GANs [closed]

What is intuition behind multimodal distribution? and How does GANs generate samples from it?
5
votes
2answers
6k views

Is there “Attention Is All You Need” implementation in Keras?

Has anyone seen this model's implementation using Keras? inb4: tensorflow, pytorch
1
vote
1answer
259 views

What exactly is the “hyperbolic” tanh function used in the context of activation functions?

I know the plot of $\tanh$ activation function looks like. I also know that its output has a range of $[-1, 1]$. Furthermore, I also know the it is defined as follows $$ \tanh(x) = \frac{\sinh(x)}{...
3
votes
1answer
918 views

Probability of dropout growth

In the DNN literature, is there analysis or a term on a dropout ratio (oppositely-)proportional to the depth of a layer? By intuition, I'd like to dropout fewer neurons on the layers next to the ...
1
vote
1answer
800 views

Words as features of a neural networks

I'm new in Machine learning and I'm working on a problem related to text. I know that in ML we can use features as numerical values as input to neural network, but I don't know how to use features as ...
1
vote
1answer
453 views

Polynomial regression vs. multilayer perceptron [closed]

Polynomial regression and multilayer perceptrons have different structures and different learning procedures. What are these two algorithms pros and cons? Are there some situations where one should ...
2
votes
0answers
49 views

Can you have too uniform test data in a feedforward neural network?

I been playing around trying to implement my own feedforward neural network. To try it out I decided on an easy example. 3 inputs, 3 output. When you send in (1,0,0)...
6
votes
3answers
8k views

Train new data to pre-trained model

Let's say I've trained my model and made my predictions. My question is... How can I append some new data to my pre-trained model without retrain the model from the beginning.
4
votes
1answer
160 views

Organization of layers in Keras for a NLP problem

I have been trying out an NLP problem where I have to predict multi-label-sentiments for some text. I have 8 labels and 170k training examples, and 140k for the test set. My final dictionary size is ...
2
votes
2answers
994 views

Neural network approach to the cocktail party effect

Imagine you have 2 people at 2 different microphones but in the same room. Each microphone is going to pick up some sound from the other person. Is there a good neural network based approach to ...
0
votes
1answer
93 views

Reason for having both low loss and same predicted class?

I'm training a cNN for binary classification. I used a batch size of 128, and the loss is decreasing and accuracy is increasing over epoches. The accuracy reached over 0.99 eventually, and the loss ...
2
votes
1answer
3k views

Watermark detection in Python

I have a lot of images and I would like to be able to classify them into two groups: one containing images with watermarks and one containing images without any watermark. There are about 40 ...
1
vote
0answers
1k views

How to perform Instance Segmentation using Tensorflow?

I used Tensorflow Object Detection API for a custom dataset based on the instructions at this help document.As required , collected the dataset,annotated it in PASCAL VOC XML format,split into ...
0
votes
1answer
31 views

Correct normalisation terminology

Take the given values: -2.998, 8.0, 2.5. My normalisation function takes a sum of the absolute values (13.498), let's call that ...
0
votes
1answer
809 views

Why does my loss value start at approximately -10,000 and my accuracy not improve?

I'm developing a multi-label classifier using the Keras library, but I am stuck with a relatively low accuracy of about 2% and my loss value per epoch is around -10,000 with little change between ...
3
votes
1answer
737 views

What are the tools to speed up the running time of machine learning algorithms? [closed]

I know Spark as the fastest tools for Data processing, but not sure if it would be useful to speed up the running time of ML algorithms. For example, my ML models to be built needs about 24h when I ...
7
votes
2answers
8k views

How to plot cost versus number of iterations in scikit learn?

One of the recommendations in the Coursera Machine Learning course when working with gradient descent based algorithms is: Debugging gradient descent. Make a plot with number of iterations on the x-...
11
votes
1answer
3k views

Using a pre trained CNN classifier and apply it on a different image dataset

How would you optimize a pre-trained neural network to apply it to a separate problem? Would you just add more layers to the pre-trained model and test it on your ...
0
votes
1answer
418 views

Convolution neural network: small dataset affecting accuracy

I have dataset of 36 folders 1 image each(total 36 images) the dataset is too small but these are character images which i want to train my val_acc= 0.0229 and <...
3
votes
3answers
2k views

What is the best way to compare various classification models?

If I have two classifiers for example Neural network and support vector machine , now I want to know what would be the best way to identify which is good classifier , should it be based on ...

1
48 49
50
51 52
66