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
0answers
293 views

What is significance of Colour-digit MNIST game in paper Learning to Communicate with Deep Multi-Agent Reinforcement Learning?

My question is regarding the paper Learning to Communicate with Deep Multi-Agent Reinforcement Learning (https://arxiv.org/abs/1605.06676). Can anyone explain what is the significance of Colour-digit ...
6
votes
1answer
127 views

How to model segmentation of a sequence to similar parts?

I guess LSTM is good for sequence modeling but how would you model "clustering" with it? Meaning, the input is a sequence and the output is labels with similar properties (I have labeled data). For ...
7
votes
1answer
1k views

What is missing from the following Curriculum Learning implementation in a Deep Neural Net?

First of all we have a classification task. So we use the typical softmax cross entropy to classify. Current implementation of curriculum learning is as follows. First we train our best version of ...
6
votes
2answers
2k views

What is the classical way to visualize 3D filters in convolutional neural networks?

Suppose that at a layer $N$ within a CNN, my "image" is a 200$\times$200$\times$10 array. Thus, if I convolve such an array with, for example, 15 filters of size 3$\times$3$\times$10, I will end up ...
13
votes
1answer
17k views

What is a 1D Convolutional Layer in Deep Learning?

I have a good general understanding of the role and mechanism of convolutional layers in Deep Learning for image processing in case of 2D or 3D implementations - they "simply" try to catch 2D patterns ...
1
vote
0answers
62 views

What is search engine life cycle from information retrieval perspective

I am already aware of usage of information retrieval for search engine. But still trying to understand what can be possible life-cycle phases for a search engine. I mean for a search engine is it only ...
5
votes
1answer
24k views

How to do imbalanced classification in deep learning (tensorflow, RNN)?

I am trying to do binary classification of News Articles (Sports/Non-Sports) using recurrent neural net in tensorflow. The training data is highly skewed [Sports:Non-Sports::1:9]. I am using cross-...
1
vote
0answers
156 views

Keras del stuck with constant loss and accuracy [duplicate]

I am trying to train a keras CNN against the Street View House Numbers Dataset. You can find the project here. The problem is that during training neither loss nor accuracy change over time. I have ...
2
votes
1answer
246 views

CNN training data size for determing the winner of tic-tac-toe

I'm trying to learn machine learning with tensorflow and wrote a program that uses CNNs to determine game results for a given tic-tac-toe board. Its inputs and outputs are - Input - An array of 9 ...
4
votes
1answer
5k views

Difference between paragraph2vec and doc2vec

Is paragraph2vec the same as Doc2vec or is every approach different?
2
votes
1answer
76 views

Regions /patterns in images that creates classification

I am having some images on which I trained some neural network models in order to do classification( binary task). I am interested of a method to identify some patterns or regions in ...
49
votes
5answers
24k views

Adding Features To Time Series Model LSTM

have been reading up a bit on LSTM's and their use for time series and its been interesting but difficult at the same time. One thing I have had difficulties with understanding is the approach to ...
5
votes
1answer
3k views

Keras CNN with low/constant accuracies

I am dealing with the Street View House Number recognition problem. I am trying to train a CNN with Keras. Here is how I prepared the input: ...
9
votes
1answer
15k views

number of parameters for convolution layers

In this highly cited paper, authors give the following discussion on the number of weight parameters. I am not very clear why it has $49C^2$ parameters. I think it should be $49C$ since each of $C$ ...
4
votes
1answer
653 views

combining trained neural nets in tensorflow

I am using tensorflow to train two instances of the same neural network with two different datasets. the network itself is quite simple with an input and output layer and 6 hidden layers (each layer ...
6
votes
2answers
222 views

Question about the simple example for batch normalization given in “deep learning” book

In the section about batch normalization of Deep Learning book by Ian Goodfellow (chapter link) there is the follwing text: As example, suppose we have a deep neural network that has only one ...
0
votes
1answer
46 views

In Recommendation systems, Does we need to build each model for each product if we are using Logistic regression?

I am reading this paper wide and deep learning recommedation system paper and haven't understood one thing. To serve the latency, they actually first get the 100 best apps according to user query ...
3
votes
1answer
141 views

Clarification wanted for make_step function of Google's deep dream script

From https://github.com/google/deepdream/blob/master/dream.ipynb ...
0
votes
1answer
314 views

Why is video classification still not that accurate?

I was wondering, with the advent of deep learning, many tasks related to images have been solved to near human accuracy such as classification, object detection etc., however in videos, traditional ...
4
votes
1answer
28k views

Using Tensorflow model for prediction

I am new to tensorflow. I have manged to train and validate a CNN, saved the session through the Saver object into a CPKT file and loaded it back. Now I'd like to use the trained model in order to ...
1
vote
0answers
392 views

Skip gram Word2Vec model, neural network implementation

I have referred and used materials from these - cs224n stanford. Following is the algorithm provided in the stanford course notes for training a skip gram model. Here |V| is the vocab size, matrix V ...
26
votes
1answer
9k views

PyTorch vs. Tensorflow Fold

Both PyTorch and Tensorflow Fold are deep learning frameworks meant to deal with situations where the input data has non-uniform length or dimensions (that is, situations where dynamic graphs are ...
0
votes
1answer
462 views

Back propagation and Structure of a Neural Network in scikit-neuralnetwork

I am trying to learn Neural Networks using scikit-neuralnetwork framework and I know basics about Neural Networks and now trying to implement it with scikit-learn. but I am confused on 2 points. 1- ...
42
votes
4answers
41k views

Why mini batch size is better than one single “batch” with all training data?

I often read that in case of Deep Learning models the usual practice is to apply mini batches (generally a small one, 32/64) over several training epochs. I cannot really fathom the reason behind this....
1
vote
1answer
357 views

How to deal with word length variability while using char-level one-hot encoding?

I am trying to run some experiments on internal word structure of morphologically rich language (Russian). Each valid character is 1-hot encoded and then fixed-length vectors are concatenated to ...
0
votes
1answer
715 views

What's a good method for combining data of different deep learning models?

Suppose I want to predict the probability of a person to buy something. I want to analyze the person image and I can use a convolutional neural network, but I also want to input in my predictive model ...
0
votes
1answer
302 views

Roadmap to learn CNN in tensorflow from scratch

I'm working in the medical field and I'd like to learn applications of CNN for image recognition and classification. All the (few) things I learned come from self-learning on the web or sparse books. ...
5
votes
5answers
5k views

Why neural networks models do not allow for multiplication of inputs?

In a neural network, each neuron value is multiplied by the weight of the connection. Then, each neuron's input is the sum of all those values, on which we apply the activation function (sigmoid, relu,...
6
votes
1answer
5k views

Keras: How to normalize dataframe with continuous and categorical data?

I have a dataframe with about 50 columns. The columns are either categorical or continuous data. The continuous data can be between 0.000001-1.00000 or they can be between 500,000-5,000,000. The ...
3
votes
3answers
2k views

Keras: X and Y are the same, yet validation accuracy is 50%, what is wrong?

I am trying to understand what is going on so I built a simpler version of my project. I set the X and the Y to be identical and I'm trying to predict Y using X, this should be very simple, but my ...
1
vote
1answer
114 views

Specifying neural network output layout for object detection

I have a question about if the modeling of the output detection affects the neural nets capability. In my case I want to train a CNN for object recognition and classification. As an output I want to ...
1
vote
1answer
2k views

Build knowledge bot using deep learning

I'm going through this chatbot example, which uses the Cornell movie dialog corpus. Expanding this example, is it possible to build a "knowledge bot" (ie) a bot that can chat and be knowledgeable in a ...
9
votes
2answers
7k views

Could Deep Learning be used to crack encryption?

Say you have a dataset with millions of rows and the attributes Plain Text, Key, and Output Ciphertext. Could Deep Learning, theoretically, be used to find patterns in the outputs that help decipher ...
8
votes
4answers
1k views

Do convolutions “flatten images”?

I'm looking for a good explanation of how convolutions in deep learning work when applied to multi-channel images. For example, let's say I have a 100 x 100 pixel image with three channels, RGB. The ...
11
votes
1answer
4k views

Reason for square images in deep learning

Most of the advanced deep learning models like VGG, ResNet, etc. require square images as input, usually with a pixel size of $224x224$. Is there a reason why the input has to be of equal shape, or ...
0
votes
2answers
116 views

Is my general understanding of finding weights correct?

I started a course in Deep Learning. I'm trying to make an example in order to explain to myself how the weights are found mathematically. If what I wrote below is nonsense I'll be glad to hear an ...
0
votes
1answer
362 views

Deep Learning: Feed Forward for Unbalanced Classes Using Tensor Flow

In theory, Deep Learning NN can predict a class with very few observations. My problem, I have a class that happens less than 4% of the time. Feeding the network data with distribution intact (96 ...
1
vote
0answers
351 views

Tips for retraining convolutional neural networks given a drastically different loss surface

For the image dataset I am working with, I need to use B&W version of images (otherwise, I would need to build a network to give false colors to a set of my images, since they have an overpowering ...
0
votes
1answer
3k views

Objects Localization Through CNN

I am new to deep learning and tensor flow and I am trying to train a CNN at localizing digits in the Street View House Numbers data set. To this end I have an input set of 32x32 images and, since I ...
0
votes
2answers
1k views

Which deep learning framework have support for gtx580 GPU? [closed]

I would like to train convolutional neural networks using a gtx580 gpu. I tried setting up TensorFlow but it did not work (wrong cuda compute compability). Which deep learning framework can best ...
7
votes
1answer
8k views

feature extraction for a pretrained model in keras

Keras has a way to extract the features of a pretrained model, described here https://keras.io/applications/ ...
2
votes
0answers
2k views

What exactly is a step in Tensorflow prebuilt architectures? [closed]

When running the object detection tutorial, you can use train.py which is supplied. On the console, the following is printed : ...
10
votes
4answers
4k views

Machine Learning vs Deep Learning

I am a bit confused by the difference between the terms "Machine Learning" and "Deep Learning". I have Googled it and read many articles, but it is still not very clear to me. A known definition of ...
2
votes
2answers
618 views

Kur vs Keras - pros and cons

I just stumbled across Kur. At first look, it seems to be making deep learning easy in almost similar lines like Keras on a high level. What are the pros and cons of each and what is suggested to be ...
4
votes
1answer
6k views

Word embedding/Word2vec for POS tagging

I am building a entity detection and relation classification method using deep learning approach which requires vector representation of POS tags and entity label. I am familiar with word-embedding ...
8
votes
1answer
4k views

What is a tower?

In many tensorflow tutorials (example) "towers" are mentioned without a definition. What is meant by that?
8
votes
4answers
11k views

Pattern Recognition on Financial Market

Which machine learning or deep learning model(has to be supervised learning) will be best suited for recognizing patterns in financial markets ? What I mean by pattern recognition in financial market ...
1
vote
1answer
308 views

Digits Localization on Streets View House Numbersm

I am trying to learn a bit of deep learning playing with the Street View House Numbers data set. I have managed to recognize sequences of digits and I'd like now to train a CNN to localize digits and ...
6
votes
1answer
2k views

Multi scale CNN Network Python

I created a multi-scale CNN in python keras. The network architecture is similar to the diagram. Here, same image is fed to 3 CNN's with different architectures. The weights are NOT shared. I ...
0
votes
1answer
2k views

Recognize Street View House Numbers

I am new to deep learning and I am trying to train a NN to recognize house numbers gathered from street view. I have already managed to recognized MNIST sequence of hand written digits by means of a ...

1 52 53 54 55 56 59