Questions tagged [neural-network]

Artificial neural networks (ANN), are composed of 'neurons' - programming constructs that mimic the properties of biological neurons. A set of weighted connections between the neurons allows information to propagate through the network to solve artificial intelligence problems without the network designer having had a model of a real system.

Filter by
Sorted by
Tagged with
0
votes
2answers
84 views

What are some general tips to improve my MNIST classifier?

I have built a CNN from scratch in python using Numpy, to tackle the MNIST hand-written digit recognition problem. It's composed out of a convolutional layer (3 3x3 filters), a maxpooling layer (2x2 ...
2
votes
1answer
294 views

should I shift a dataset to use it for Time series regression with RNN/LSTM?

I'm seeing this tutorial to know how to use LSTM to predict time series data and I noticed that he shifted the target/labels up so that the features are all in time t but the target is t+1 so my ...
0
votes
1answer
21 views

Need help understanding how this Neural Network is working

This is a model I came across, and I need some help understanding how it works It uses South German Credit Prediction data set from Kaggle ...
1
vote
3answers
64 views

What is exactly the difference between Validation data and Testing data

I asked this question on stack overflow and was told that this is a better place for it. I am confused with the terms validation and testing, is validating the model same as testing it? is it possible ...
0
votes
0answers
5 views

Auto ML for feature engineering

Is there any Auto ML that can try different feature engineering approaches, encoding, feature selection based on importance etc? I have been manually trying different encoding techniques for ...
0
votes
1answer
2k views

ValueError: Tensor Tensor("activation_5/Softmax:0", shape=(?, 2), dtype=float32) is not an element of this graph

There seem to be an issue with predicting using my keras model. I had trained it using the following keras code: ...
0
votes
1answer
15 views

About neural network ability to generalize

I had this question during an interview that I wasn't able to answer, even after researching on the internet. Which of the following can affect an artificial neural network’s ability to generalize??? ...
0
votes
1answer
41 views

Custom layer for Simple Exponential Smoothing

I am writing a test custom layer which implements the Simple Exponential Smoothing algorithm. The problem: when I train it, the alpha (smoothing) coefficient always converges to value 1. This means ...
0
votes
0answers
5 views

How to pass multiple vectors to a RNN/LSTM network and get output as a vector. Can someone explain or give reference to code/text

I need to feed multiple vectors to a RNN/LSTM and get a vector as output utilizing dependencies between the vectors . How do i pass the vectors . Is there any code/reference ?
2
votes
2answers
88 views

Is a neural network able to learn to map a completely different feature vector to the same class

Is a neural network (for example a MLPClassifier in Python) able to learn to map a completely (or very) different input feature set to the same output class? Or is it better to work in this case with ...
3
votes
4answers
23k views

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int) in Python

I have written the following code for a neural network to perform regression on a dataset, but I am getting a ValueError. I have looked up to different answers and ...
0
votes
1answer
206 views

Mask R-CNN Background Subtraction Implementation

I am currently attempting to reimplement a paper on fall detection (https://ieeexplore.ieee.org/abstract/document/9186597). It requires a background subtraction algorithm called Mask R-CNN. Are there ...
0
votes
0answers
17 views

How to use hierarchical variable in a ML model

I am working on a binary classification problem with 1000 rows and 20 variables. I have variables like product_id, city, ...
0
votes
1answer
10 views

Input- and Output Data Shape Difficulty

I'm a Keras beginner. My main problem right now is how to build a model that suits my data. For the Model itself I'd like to build it so the inputs/outputs are: Input Data: (List that contains) three ...
0
votes
1answer
17 views

Recommendation for Math Focused Neural Network Book

I am looking for textbooks on Neural Networks with a strong focus on their math. I need something with proofs and theorems, principally on convergence criteria.
2
votes
1answer
391 views

How to represent the number of neurons in an LSTM for architecture schematic?

I'm trying to visualise a neural network schematic and found a great tool for building schematics here http://alexlenail.me/NN-SVG/index.html. I've edited the SVG file to change one of the dense ...
1
vote
0answers
15 views

Which ML to use for search suggestion?

Problem: I want to create a program to organize text information and fast access to relevant documents. I would like to train a ML model to analyse the current situation and to suggest the next ...
0
votes
0answers
6 views

Model does not learn after ternarization of weights contrary to the paper mentioned below

I’m implementing the ‘Ternary Weights Network’ paper by Fengfu Li and Bo Zhang ( archive link - https://arxiv.org/abs/1605.04711). I’m training a simple Covnet with linear layers on the MNIST dataset. ...
1
vote
1answer
150 views

What program to use to visualise neural network diagram and math functions

I am writing a paper about machine learning and I need to create some neural network diagrams and basic math functions I am describing. I need a program to create visually decent technical picture ...
0
votes
0answers
13 views

What happens if you don't include any activation function on hidden classification layers?

What happens if we don't apply an activation function to the classification hidden layers and apply it only for the final output layer (Sigmoid, Softmax)? I'm asking this because I have trained a CNN ...
0
votes
0answers
7 views

Output Network in the algorithm

Can somebody explain how to understand/interpret the output network in the algorithm below? This image is taken from the article https://arxiv.org/pdf/1907.03907.pdf (3rd page).
2
votes
1answer
47 views

Is data subsampling appropriate for hyperparameter optimisation?

Fundamentally, under what circumstance is it reasonable to do HPO only on a subsample of the training set? I am using Population Based Training to optimise hparameters for a sequence model. My dataset ...
1
vote
1answer
2k views

keep_dims is deprecated, use keepdims instead

I downloaded: !git clone https://www.github.com/matterport/Mask_RCNN.git os.chdir('Mask_RCNN') And I've got an error: which version I should have of Keras? <...
1
vote
1answer
2k views

Custom loss function with multiple outputs in tensorflow

my network has two outputs and single input. I am trying to write a custom loss function $$ Loss = Loss_1(y^{true}_1, y^{pred}_1) + Loss_2(y^{true}_2, y^{pred}_2) $$ I was able to write a custom loss ...
1
vote
1answer
95 views

activation function for binarized neural networks

I am trying to implement a binarized neural network using keras and tensorflow. Here is my current code: ...
3
votes
1answer
1k views

Overfitting in CNN

I am training a VGG net on STL-10 dataset I am getting Top-5 validation accuracy about 98% and Top-1 validation accuracy about 83% But both the Top-1 and Top-5 Training accuracy is reaching 100% ...
0
votes
3answers
45 views

Interpretation of learning curve - neural network

When I run my three different neural networks I obtain the following learning curves using MSE. I believe that my model base is okay and is not overfitting or underfitting. Furthermore, I believe ...
1
vote
1answer
1k views

How to use Keras Linear Regression for Multiple input-output?

I was trying to use this code. I put part of the parameter list, but as you see the error indicates that it's taking the first member of each list to put in the first row and second ones for the ...
1
vote
2answers
294 views

Why the first prediction of neural network in PyTorch is slower than following predictions?

So I have ResNet50 trained to classify images. For each prediction I track the time needed for it (input and model are moved to GPU): ...
1
vote
0answers
31 views

Sigmoid activation functions do not seem to cause vanishing gradients

I have fitted a feedforward NN on the Pima diabetes data. The data consists of 8 features and 1 binary response. My model consists of 3 hidden layers parameterised by logistic sigmoid activation ...
3
votes
2answers
1k views

Perceptron - Which step function to choose

I'm studying Perceptron algorithm. Some books use this step function 1 if x>=0 else -1 where x is a dot product between the weights w and a sample x. Other ...
2
votes
0answers
22 views

Variance of Jacobian in backpropagation

Glorot and Bengio introduced the Glorot uniform initialisation in their 2010 publication. My question concerns some details in the derivation, specifically how equation (2) leads to equation (6). I ...
1
vote
1answer
43 views

Autoencoder not learning walk forward image transformation

I have a series of 15 frames with (60 rows x 50 columns). Over the course of those 15 frames, the moon moves from the top left to the bottom right. Data = https://github.com/aiqc/AIQC/tree/main/...
4
votes
2answers
101 views

What are the reasons for drawing initial neural network weights from the Gaussian distribution?

Are there theoretical or empirical reasons for drawing initial weights of a multilayer perceptron from a Gaussian rather than from, say, a Cauchy distribution?
0
votes
1answer
41 views

AutoML for categorical feature encoding

I have an input dataset with more than 100 variables where around 80% of the variables are categorical in nature. While some variables like gender, country etc can be one-hot encoded but I also have ...
13
votes
4answers
1k views

Do neural networks have explainability like decision trees do?

In Decision Trees, we can understand the output of the tree structure and we can also visualize how the Decision Tree makes decisions. So decision trees have explainability (their output can be ...
2
votes
1answer
38 views

exclude variables with no variation during prediction?

I am working on a binary classification problem. I do have certain input categorical variables such as gender, ethnicity etc. ...
1
vote
0answers
31 views

Why we call Mix-up method is a data augmentation technique?

I am bit confused in the Mixup data augmentation technique, let me explain the problem briefly: What is Mixup For further detail you may refer to original paper . We double or quadruple the data ...
0
votes
2answers
81 views

Validation loss and validation accuracy stay the same in NN model

I am trying to train a keras NN regression model for music emotion prediction from audio features. (I am a beginner in NN and I am doing this as study project.) I have 193 features for training/...
1
vote
2answers
167 views

Designing a pretrained DNN for image similarity

I am pretty new to deep learning and really hope that you can help me. I want to write a python program that lets me choose an area in a reference image. This subimage of variable size should then be ...
2
votes
1answer
55 views
1
vote
1answer
570 views

Accuracy and Loss in MLP

I am trying to explore models for predicting whether a team will win or lose based on features about the team and their opponent. My training data is 15k samples with 760 numerical features. Each ...
-1
votes
0answers
9 views

Training and Validation loss are same but not decreasing for LSTM model

I have a timeseries data and I am doing univariate forecasting using stacked LSTM without any activation function, Like following. ...
0
votes
1answer
21 views

How to use rule-based labelling intelligently?

I have a dataset like below The outcome column is labelled as positive if the % difference between target final Qty and ...
2
votes
1answer
313 views

Problem when cherry picking actions - Proximal Policy Optimization

I am using the implementation of PPO2 in stable-baselines (a fork of OpenAI's baselines) for a Reinforcement Learning problem. My observation space is $9x9x191$ and my action space is $144$. Given a ...
0
votes
0answers
13 views

Saturation of exponential linear units (ELU)

The ELU activation function saturates to $-a$ for large negative inputs. \begin{align} f(x) = \left\{ \begin{array}{rcl} a(\text{exp}(x) - 1) & \mbox{for } x \leq 0 \\ x & \...
0
votes
1answer
100 views

the size of training data set in the context of computer vision

Generally speaking, for training a machine learning model, the size of training data set should be bigger than the number of predictors. For a neural network, or even a deep learning model, the number ...
0
votes
0answers
5 views

Update tensorflow model with new data

I have trained the time series prediction model using old data, and as time goes by, I get more data and want to update my model with it. But it seems like my model perform worse as I update the model....
2
votes
0answers
204 views

Maximum number of classes YOLO net can recognize on mobile

I'm trying to make a mobile app on image recognition(Computer Vision Application) . Does anyone know whether modern day smartphones have enough processing power/memory to recognize, say about 1 ...

1
2 3 4 5
80