Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange
Join us in building a kind, collaborative learning community via our updated Code of Conduct.

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 sorts of Probabilistic Graphical Models.

0
votes
0answers
3 views

Resource and useful tips on Transfer Learning in NLP

I have a few label data for training and testing a DNN. Main purpose of my work is to train a model which can do a binary classification of text. And for this purpose, I have around 3000 label data ...
1
vote
1answer
5 views

Predicting Composition of Chemical Compounds

I have a dataset which has names of compounds and their compositions. Like below Sulphuric Acid=>[H,S,O] (Hydrogen, sulphur, oxygen) Oxalic Acid=>[H,C,O] Sodium Oxalate=>[Na,C,O] Potassium Sulphate=>[...
2
votes
2answers
15 views

Deep Neural Network: Output a Magnitude, not merely a Category

How does (can?) a deep neural network provide a magnitude estimate, rather than simply guessing what category an input belongs to? For example, in guessing the weight of a cat, is there is a ...
2
votes
0answers
8 views

Fully connected layer output explodes, but weights, gradients, and inputs all have sane values

I'm trying to train a GAN, and the architecture includes a fully connected layer before the output activation function. In my case, by the second training iteration this layer's output always explodes....
1
vote
2answers
15 views

How to use Cross Entropy loss in pytorch for binary prediction?

In the pytorch docs, it says for cross entropy loss: input has to be a Tensor of size (minibatch, C) Does this mean that for binary (0,1) prediction, the input must be converted into an (N,2) ...
0
votes
1answer
7 views

Can I use fit() function with images in Keras?

I want to use vgg16 to train a dataset that contains images. Can I use fit() function instead of fit_generator() in Keras? How?...
1
vote
0answers
12 views

How to implement YOLO in my CNN model?

I build a CNN model using keras on the cat vs dog dataset. Now what I want is with the image classification my model should also locate that animal on that image. I searched on web and found that YOLO ...
2
votes
1answer
19 views

What is wrong with this reinforcement learning environment ?

I'm working on below reinforcement learning problem: I have bottle of fix capacity (say 5 liters). At the bottom of bottle there is cock to remove water. The distribution of removal of water is not ...
1
vote
1answer
22 views

How to give rewards to actions in RL?

I'm working on below reinforcement learning problem: I have bottle of fix capacity (say 5 liters). At the bottom of bottle there is cock to remove water. The distribution of removal of water is not ...
1
vote
0answers
16 views

Intuition / Importance of intermediate supervision in deep learning

These days, I have seen many papers using intermediate supervision. Single Network When using a single neural network, multiple neurons output predictions, perhaps by processing data in different ...
1
vote
2answers
17 views

CNN, which layer to choose for a similarity measure

I built a model (InceptionResnet v2) to classify images and I would like to use it to measure similarity between objects. One way to measure that similarity is to catch an intermediate layer's ...
0
votes
1answer
32 views

Interpretation & interpretability of machine learning models

What is the current status on the interpretation & general interpretability of machine learning models? Any links would be highly appreciated.
0
votes
0answers
10 views

ValueError: Cannot feed value of shape (32,) for Tensor 'Placeholder_1:0', which has shape '(?, 10)'

When I run this on my own PC it works. But, when I switch it to Google Colab it returns "ValueError: Cannot feed value of shape (32,) for Tensor 'Placeholder_1:0', which has shape '(?, 10)'" What's ...
1
vote
0answers
12 views

K-fold cross validation when using fit_generator and flow_from_directory() in Keras

I am using flow_from_directory() and fit_generator in my deep learning model, and I want to use cross validation method to train ...
1
vote
0answers
18 views

Deep Q-Learning with large number of actions

I'm using DQN with large number of actions in [0, 10000, step = 1000]. This means I have an action space of size 11 (including 0 and 10000). Action space is still discrete. My problem is that, instead ...
0
votes
0answers
30 views

Tensorflow deep learning Weird Accuracy

I want to build a model to classify images of a dataset( ASL signs alphabet ). The dataset is in a folder where each sub-folder contains the images of a class and the name of the class is the name ...
1
vote
1answer
6 views

CNN to learn and visualize 2d features

In the paper Large-Margin Softmax Loss for Convolutional Neural Networks the author has a figure as below: He is claiming that he is using only 2d features to classify MNIST with a CNN. How is he ...
0
votes
0answers
4 views

Attention model - How to deal with variable feature dimension?

In the paper "SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints"section 3.3 the authors mentioned that $V^t_{si}$ is generated via concatenation i.e. $V^t_{si}...
0
votes
1answer
15 views

I need sources of interrogative, exclamatory, and imperative sentences

I am working on accumulating a large database of labeled sentences for several projects/experiments. At present I am only using Wikipedia and Project Gutenberg as sources of data. Between these two ...
0
votes
1answer
18 views

how to save deep learning model and test it after training?

I have a CNN model written using tensorflow for python, the model is for classifying lung CT images (cancer/no-cancer), after training the model with training and validation data and get a reasonable ...
0
votes
0answers
11 views

What research is this similar to — Deep CNN for generating images by classifying individual pixels — not a GAN [on hold]

Generative adversarial models (GAN) use deconvolution to generate images (generator model) combined with convolution to distinguish between real and generated (determinator). However, multiple models ...
-1
votes
2answers
17 views

two dimensional list takes huge amount of memory

I have a 2d list which is created from lung CT image data and a label (the first item is a 3d array(image data) and the second item is a label(0 or 1)), I need this to data to train CNN model, the ...
1
vote
1answer
30 views

Evaluating metrics F1, F2, Mean Average Precision for object detection

Up today in the company where I work we are using the F1 Score for evaluating the performance of our model, also our competitor's using the same metric. I would like to understand what's the ...
2
votes
1answer
19 views

Difference between advantages of Experience Replay in DQN2013 paper

I've been re-reading the Playing Atari with Deep Reinforcement Learning (2013) paper. It lists three advantages of experience replay: This approach has several advantages over standard online Q-...
1
vote
1answer
31 views

Why is predicted rainfall by LSTM coming negative for some data points?

I have used supervised learning with LSTM network using tanh activation function and 0.1 dropout for time series prediction.my loss='mean_squared_error', optimizer='adam'. The predicted time series is ...
0
votes
0answers
7 views

How to find correlation among multiple attributes in group by dataframe object?

I have a data frame with following attributes : CP - Counting point of vehicles A-Junction - Starting node of a road ...
1
vote
0answers
32 views

Loss function for Hierarchical Multi-label classification

I am looking to try different loss functions for a hierarchical multi-label classification problem. So far, I have been training different models or submodels (e.g., a simple MLP branch inside a ...
1
vote
0answers
19 views

same model gives different values

I built a MLP for classification problem. I used KDD99 dataset. but the problem is that when I run it it gives ech time a different value of accuracy. Is this logic? I mean could the same model for ...
1
vote
1answer
26 views

How to display the value of activation?

I have built my network and would like to see how the activation of a particular layer change after each epoch of training. For example, as code shown below, I want to see the activation values of "...
0
votes
0answers
7 views

RNN model with 3 hidden layers

In a paper, it mentioned: ANN, RNN, and LSTM NN are optimized to contain three hidden layers with 1000 hidden units in each layer. I would like to model the RNN model in Keras. But my code fails in ...
0
votes
3answers
37 views

can machine learning/Deep learning used to minimize an objective function?

I have data of construction site and am wondering if i can use machine learning to reduce the cost it takes to build a building. But, as far as i know, Machine learning can only does function ...
4
votes
2answers
687 views

Should use sklearn or tensorflow for neural networks?

I have just started learning Neural Networks for deep learning from cs231. I am trying to implement Neural Network in Python. I am looking at using Tensorflow or scikit-learn. What are some pros and ...
2
votes
1answer
31 views

Is GEMM used in Tensorflow, Theano, Pytorch

I know that Caffe uses GEneral Matrix to Matrix Multiplication (GEMM) which is part of Basic Linear Algebra Subprograms (BLAS) library for performing convolution operations. Where a convolution is ...
0
votes
0answers
7 views

How to train deep Boltzmann Machines?

For simplicity, suppose that I have a deep Boltzmann machine with two RBM layers stacked on each other with hidden variables $h_1$ and $h_2$. And suppose that I already know how to train the first ...
0
votes
1answer
23 views

How to verify hand written signature?

I trying to create a model for determining whether a questioned hand written signature matches known signature samples, and predict if the signature is genuine or forgeries. I'm guessing I'll have to ...
1
vote
2answers
14 views

Setting batch size: training requires twice as much memory as validating

I am using Keras with a Tensorflow backend to train an Image Classification model on a GPU. I have read somewhere that training uses roughly twice (both forward and back props) the GPU memory of ...
1
vote
0answers
18 views

How to calculate the level of sparsity of a deep learning model (CNN/MLP)? [closed]

Recently I am studying on the sparsity of the deep learning model (CNN/MLP). I am using Tensorflow as the framework to build the models, but how to calculate the level of the sparsity of each ReLU ...
1
vote
1answer
24 views

How to utilize user survey answers and the actual usage in forecasting power usage using LSTM?

I have the pre-trial survey and post-trial survey conducted of around 5000 users for Smart Meter installation. With this I have power usage reading recorded every 30 min for around one and a half ...
3
votes
1answer
37 views

How to make it possible for a neural network to tune its own hyper parameters?

I am curious about what would happen to hyperparameters when they would be set by a neural network itself or by creating a neural network that encapsulates and influences the hyperparameters of the ...
1
vote
1answer
25 views

General equation - calculating backpropagation [closed]

How to calculate new weights for neurons - what is the general equation for it?
1
vote
0answers
16 views

using deep learning with kares to produce ANN model Error: could not convert string to float: '2014-04-02 17:50:04'

i am trying to fit a model a using deep learning with kares to produce ANN model using the following code Load libraries ...
1
vote
0answers
11 views

Is it possible to train for precision in Tensorflow?

Can I train a binary classifier in Tensorflow to maximize precision?
0
votes
1answer
17 views

Backpropagation - simplest explanation

Could you please explain in simplest way the algorithm (mathematical equation) of back-prop? I read lot of articles, I know for what it is, and I understand the intuition behind it, but I still don't ...
0
votes
0answers
14 views

increase accuracy of DNN tfestimator in r

I'm trying to use tfestimator for purchase prediction that the customer will be either a purchaser or not. For this purpose, I used deep neural networks using the code mention below. ...
0
votes
0answers
9 views

Why my Simple DL model with default SGD working very poorly in keras?

When I'm answering questions in StackOverflow, I found this question about the poor performance of DL model. I tried to implement the same code in my machine to see whats happening. I have also ...
-1
votes
1answer
23 views

Classification algorithms and deep learning

Nowadays we see a big trends of deep learning and a lot of applications using it . So, I was wondering do people still need to use the classification algorithms (traditionnal machine learning ) ?
1
vote
0answers
15 views

Oversampling for multi-class neural net

Does this make sense or do I have no idea what I'm doing? I want to train a model that takes a sentence and outputs a binary multi-class vector of size $K$ where each dimension is a question class. ...
1
vote
1answer
11 views

Are view() in Pytorch and reshape() in Numpy similar?

Are view() in torch and reshape() in Numpy similar? view() is applied on torch tensors to ...
1
vote
2answers
24 views

Few activation functions handling various problems - neural networks

How can a few activation functions in neural networks handle so many different problems? I know some basics theory behind ANN, but I can't get what functions like the sigmoid function etc. have in ...