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
30 views

Rephrase Neural Network: Where to Start? [duplicate]

I'd like to solve the problem that denoted in the below picture. With which network could I try and start to solve this problem?
5
votes
0answers
52 views

Choosing the right model to learn [closed]

I'm new to the data science world, and I hope to solve a problem using deep learning methods, I started learning how FNN and CNN work and when I saw how many models and methods are the I got a bit ...
3
votes
1answer
221 views

Best image PPI for computer vision deep learning algorithms

For computer vision tasks using deep learning, should I worry about image size (e.g. 256 x 256) or PPI (pixels per inch)? I find that PPI is not discussed in the computer vision/deep learning ...
2
votes
0answers
73 views

How to combine heterogeneous image features extracted with different algorithms for similar image retrieval?

Say I have access to several pre-trained CNNs (e.g. AlexNet, VGG, GoogleLeNet, ResNet, DenseNet, etc.) which I can use to extract features from an image by saving the activations of some hidden layer ...
3
votes
1answer
378 views

How to properly represent a tic tac toe board to a CNN?

I'm figuring out how to manipulate convolutional neural networks (CNN) in python and I want to apply this kind of NN to an agent player that plays tic tac toe. I know that's weird and the problem ...
2
votes
1answer
503 views

XOR problem with neural network, cost function

I am having a problem understanding the cost function in a neural network. I have read many books and blog posts, but all of them describe that point in neural networks is to minimize the cost ...
1
vote
1answer
955 views

Keras/Theano custom loss calculation - working with tensors

I'm struggling to write some tensor manipulation code for a custom loss function I'm using in Keras. Basically, I'm trying to modify a binary_crossentropy loss by adding a weight that is calculated ...
0
votes
1answer
185 views

Very Deep Convolutional Networks for Text Classification: Clarifying skip connections

Question RE this research paper if anyone has experience with CNN's, pooling & skip connections: https://arxiv.org/pdf/1606.01781.pdf In figure 1, the input to the first convolutional block has ...
-2
votes
1answer
975 views

Best way to extract information from text description and match it with set of words

I have 10k records of data, each record represents a unique product(10k class labels) and its description. For example, "Coffee Maker, this product takes coffee beans and brew it, to make tasty cofe". ...
6
votes
2answers
15k views

weighted cross entropy for imbalanced dataset - multiclass classification

I am trying to classify images to more then a 100 classes, of different sizes ranged from 300 to 4000 (mean size 1500 with std 600). I am using a pretty standard CNN where the last layer outputs a ...
9
votes
1answer
4k views

What is difference between Fully Connected layer and Bilinear layer in CNN?

What is the difference between Fully Connected layers and Bilinear layers in deep learning?
1
vote
2answers
161 views

problems during training a MLP type of network

I trained a neural network model, a MLP type of network, where the first several layers are 1-D convolution for processing sequence type of input. However, the training process looks like as follows, ...
1
vote
1answer
144 views

Can I install Tensorflow in Anaconda without using Keras?

Can I install Tensorflow in Anaconda without using Keras? If I can what is the difference between using Keras with Tensorflow and only Tensorflow? Thanks..
1
vote
0answers
16 views

Model for 'Pattern to Pattern'?

How to create a model that will generate a similar pattern/image? And how sould I address it, if I only have 400 exmples after the augmentation. This is the kind of data I have (16X16) 0,0,0,0,0,0,0,...
2
votes
1answer
75 views

How to determine the number of forward and backward passes in deep learning (CNN)? [closed]

Is there a way to determine the number of forward and backward passes in the training of a neural network using python?
1
vote
1answer
519 views

LSTM not learning with extra nontemporal data added after LSTM layer - Keras

I have three different inputs I would like to send into my LSTM - the sequence of "words", extra temporal information, as well as extra nontemporal information. Following Adam Sypniewski excellent ...
1
vote
4answers
2k views

Sparse connections in feedforward network tensorflow or pytorch?

I want to create sparse feed-forward networks in Pytorch and Tensorflow, i.e., say each node is only connected to k number of neurons of the next layer where k is strictly less than the total number ...
1
vote
0answers
101 views

What is the best deep learning architecture for image classification with different intra-class variances?

I implemented a CNN image classifier with three classes. The samples belonging to the first class have a low variance (patterns and colors are very similar from image to image). The samples from the ...
3
votes
1answer
54 views

Why does Q-learning use an actor model and critic model?

I'm currently reading Hands on Machine Learning with Scikit-Learn & Tensorflow, and I'm wondering why does Q-learning require an actor model and a critic model to learn? On page 465, it states: ...
1
vote
1answer
416 views

machine learning application in ticket pricing

I want to sell a day-pass and month-pass ticket, the price is segmented based on customers' residential community or other factor. I would like to know the pricing strategy by which I can get profit ...
3
votes
0answers
384 views

What are towers in inception architecture and tensorflow?

My understanding of towers in inception architecture and in tensorflow terminology is that they are part of a neural network model for which separate computation can happen on forward phase and ...
2
votes
0answers
56 views

Gradient of a sum

I have a neural net (BEGAN Generative Adversarial Network) where I need to apply this formula: And this one: So I made an operator that does each operation and outputs a value for each losses. Now, ...
19
votes
1answer
4k views

How to add non-image features along side images as the input of CNNs

I'm training a convolutional neural network to classify images on fog conditions (3 classes). However, for each of about 150.000 images I also have four meteorological variables available that might ...
1
vote
1answer
558 views

What is the input space of a neural network (or other supervised learning algorithms)?

While training the neural network (or any other supervised learning algorithms), we supply input variables and corresponding outputs. The input variables can be continuous or discrete (binary in many ...
0
votes
1answer
69 views

What does 1024 by 3 model mean?

I was watching this video and Sentdex mentioned he had to switch around 1024 by 3 model. What does he mean by 1024 by 3 model and what did he change around? Edited: Youtube link with the timestamp ...
1
vote
0answers
164 views

plateaus and local minima in deep learning [duplicate]

Why training deep learning models is more likely to suffer from plateaus than local minima? Could anyone illustrate it.
3
votes
0answers
959 views

What is the minimum number of times a word needs to appear in word2vec training corpus for quality results?

When training a word2vec model with, eg, gensim, you can specify the minimum times a word needs to be seen (with the parameter min_count). The default value for this seems to be 5. Are there any ...
2
votes
1answer
489 views

Unable to overfit using MLP

I'm building a 5-class classifier with a private dataset. Each data sample has 67 features and there are about 40000 samples. Samples of a particular class were duplicated to overcome class imbalance ...
0
votes
1answer
69 views

Encoder-Decoder performance time

I have two encoder-decoder models. *First model: *Second model: When I check the performance of the models I get approximately the same performance time (First model ~ 42 sec, Second model ~ 40 ...
1
vote
0answers
440 views

Regression Neural Network using tflearn

I have a script which I wrote using python and tflearn. I created a regression neural network model which takes in chemical analysis of wine as input and predicts a score out of 10. Dataset: http://...
1
vote
0answers
40 views

How do you use Tensorboard to visualise my Chatbot? What can I learn from it?

I am currently learning DeepLearning and wanted to ask a few questions in relation to my current project https://github.com/deepcollege/deeplearning/blob/master/030-chatbot/chatbot_simple.py First of ...
3
votes
1answer
84 views

What is the main goal of using activation function in CNN?

What is the main goal of using an activation function in CNN? I know the activation functions types and the purpose of each one. But here I am asking why to use them.
8
votes
3answers
3k views

What is normalization for?

I am new in python and data science (and not great in math). I am learning machine learning. I got following normalize function. Can you please explain what does this normalize function do? ...
1
vote
1answer
127 views

Rephrase Neural Network : Find the Fittest Word for Given Meaning/Explanation

I am a sophomore student who's interested in deep learning and its method layering up some linear/non-linear operations and constructs up the complex function through the network. I'd like to ...
1
vote
2answers
105 views

data pre-processing before feeding into a deep learning model

Generally speaking, when training a deep learning model, like MLP, what kind of data pre-processing operation has to be conducted when the input is a numerical sequence.
2
votes
2answers
480 views

Help me choose a Data Science book in Python [closed]

I've been a Data Scientist for a few years now, but I've only recently started to do most of my work in Python (boy, do I miss ggplot2! But ...
6
votes
4answers
13k views

How to improve accuracy of deep neural networks

I am using Tensorflow to predict whether the given sentence is positive and negative. I have take 5000 samples of positive sentences and 5000 samples of negative sentences. 90% of the data I used it ...
3
votes
3answers
1k views

Evaluation methods for multi-class classification

I am looking for single-number evaluation method that can be used in multi-class classification tasks that take into account imbalanced data-sets. For instance, ...
1
vote
1answer
2k views

Creating labels for Text classification using keras

I have a text file with information that needs to classified based on keywords. The text file contains many number of paragraphs. And the paragraph contains keywords that we want (lets say salary ...
2
votes
1answer
118 views

why is mse training drastically different from the begining of each training with Encoder-Decoder

I am using encoder-decoder model to predict binary images from grayscale images. Here is the model ...
1
vote
1answer
117 views

Understanding cnn [closed]

I'm a computer science student and one of my professors ask me if I can use cnn to make a python application which detect tumors can anyone please guide me if that is possible, to understand cnn and ...
4
votes
3answers
5k views

Number of Fully connected layers in standard CNNs

I have a question targeting some basics of CNN. I came across various CNN networks like AlexNet, GoogLeNet and LeNet. I read at a lot of places that AlexNet has 3 Fully Connected layers with 4096, ...
2
votes
1answer
2k views

Very long sequence in neural networks

Beginner's question regarding sequences in neural networks: suppose I have classification problem that looks like: X = very long sequence of varying length. Y = class (assume for simplicity y=0/1). ...
1
vote
1answer
211 views

Visitor's probability to purchase on eCommerce site, based on aggregate historic data

On an eCommerce website we want to create some personalization for visitors who are more likely to make a purchase. Let's assume we only have one single item for sale. The likelihood should be based ...
0
votes
1answer
1k views

Advantages of one shot learning over image classification

This is a rather conceptual question. From what I've read I gather that one shot learning is useful for use cases in which you don't have datasets of millions of images of employees etc. By a one shot ...
1
vote
1answer
656 views

Why are policy gradients on-policy?

I'm not entirely sure why policy gradients have to be on-policy and have to update using trajectories sampled from the current behaviour. In REINFORCE, the loss function is determined by the log ...
20
votes
2answers
13k views

What does Logits in machine learning mean?

"One common mistake that I would make is adding a non-linearity to my logits output." What does the term "logit" means here or what does it represent ?
2
votes
0answers
837 views

Test data predictions yield random results when making predictions from a saved model

I am classifying aerial imagery that is tiled into 256x256 tiles using Keras and TensorFlow. The model splits the training data (i.e. the 256x256 image tiles making up the study area) into 70% ...
6
votes
2answers
4k views

What are the cases where it is fine to initialize all weights to zero

I've taken a few online courses in machine learning, and in general, the advice has been to choose random weights for a neural network to ensure that your neurons don't all learn the same thing, ...
6
votes
4answers
2k views

Why choose TensorFlow?

I have noticed that most of the deep learning developers use TensorFlow. So why choose TensorFlow? What is the advantage of TensorFlow over Theano and CNTK?

1
49 50
51
52 53
70