Skip to main content
Share Your Experience: Take the 2024 Developer Survey

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
0 votes
1 answer
3k views

what is correct way to perform normalization on data in Auto encoder?

working on anomaly detection problem. i'm using auto-encoder to denoise given input. I trained network with normal data(anomaly free). so model predict normal state of given input. Normalization of ...
2 votes
3 answers
1k views

Detect the time at which deviation occurs in time series data

I working on multivariate time series data. I have sensor data generated by a machine every time it is operated. Data set consists of machine_ID(machines of same model), hours_ operated, measurements ...
3 votes
1 answer
688 views

Calculation of Output in LSTM Many-to-One Architecture

I'm new to Recurrent Neural Network but I want to train my data with LSTM but I'm having a trouble to understand LSTM Many-to-One architecture. Suppose the size of my data is ...
1 vote
2 answers
277 views

Statistical significance test in deep learning for regression problems

I was reading the tutorial "Statistical Significance Test for comparing ML algorithms", where it suggests to use k-fold and apply the appropriate statistical test. Suppose that I have a train set and ...
4 votes
2 answers
7k views

Saving and loading keras.callbacks.History object with np.save and np.load

I have been saving my training history in keras as follows: ...
0 votes
1 answer
218 views

DQN not learning anything - Reinforcement Learning

I am trying to train a DQN to play the 8puzzle game. I have implemented a batched gameboards, so I am not using ReplayMemory. Here's training process: ...
3 votes
1 answer
718 views

How to replace the clothes of person using GAN?

I have one source video, let us say if the person is standing or walking in the video, the person's clothes should swap with the destination image (contain the picture of any clothes). I would like to ...
0 votes
0 answers
38 views

Tensorflow SegNet architecture

I was unable to find a complete description of the SegNet architecture for image segmentation (specifically, the decoder layers). Therefore, I would like to clarify the correctness of my ...
-1 votes
2 answers
4k views

AttributeError: 'NoneType' object has no attribute 'landmark'

I am on windows, using jupyter notebook, Mediapipe:Holistic Solution, Python, tensorflow. I am using a Holistic solution and trying to get the left hand, right hand and pose landmarks. I am giving my ...
0 votes
1 answer
59 views

Are there any R packages that support Deep RNNs?

I recently found an interesting paper on what it really means for a recurrent neural network (RNN) to be deep here. Depth can be added in several different ways (state to state, input to state, etc.) ...
0 votes
2 answers
295 views

In practice, what is the cost function of a neural network?

I want to ask a fairly simple question I think. I have a deep background in pure mathematics, so I don't have too much trouble understanding the mathematics of the cost function, but I would just like ...
2 votes
2 answers
1k views

Using categorical and continuous variables in Deep Learning

I would like to apply a MLP to some business seller data. I found that the data is a mix of both categorical and continuous features. For what I read it is not advisable to feed a neural network with ...
1 vote
0 answers
17 views

Recreating results from Research Paper

so I have been trying to recreate the results from this particular paper (Neural Collaborative Filtering). The dataset I use closely resembles this . I understand that I should my data into train and ...
3 votes
2 answers
138 views

ConvNet with concatenated data

I have a basic question regarding convolutional neural network. Assume I have a set of 1000 RGB images and I train a CNN from this set. I can obviously split each of my RGB images into 3 different ...
1 vote
2 answers
360 views

Facial recognition on offline images

I want to do facial recognition on wide varieties of images captured at various ages of my family members. Below are some of the questions I have. If a person uses glasses of different types, do I ...
0 votes
1 answer
99 views

Using text classification for system calls

I'm working on a project in which I should classify System calls sequences, my dataset is represented as sequences of integers (from 1 to 340). To do the classification I have inspired from Text ...
0 votes
1 answer
556 views

What is the best way of combining audio and visual data to make predictions?

I am trying to predict the probability of a disease by using audio and images, the audio and the images do not come from the same source. I am thinking of combining the outputs (maybe average them) of ...
0 votes
2 answers
212 views

Dense layer: how to transform hgih dim vector to one dim? (sigmoid function)

I have a dense layer who transforms a 100 dimensional vector to a 1 dimensional object using a sigmoid function. I understand how a sigmoid function transforms a number to a number between 0 and 1. ...
0 votes
1 answer
487 views

How is the hidden state of a GRU initialized

This is a GRU. Now, what will be the value of $h_t$, at $t$=$0$. That is, what will be the value of the hidden state at just the starting?
3 votes
1 answer
244 views

stacking features vs concatenating layers

I am trying to get to the logical intuition of differences between stacking multiple features and passing it via a final block (which could comprise multiple layers and lets say a final classification ...
1 vote
1 answer
284 views

How to Prepare data for LSTM

I'm having difficulties to wrap my head around how I can prepare my dataset to train an LSTM. Below is a screenshot of a subset representation of my dataset. There are several other feature not ...
0 votes
1 answer
1k views

Number of input and output channels of MAX POOL layer

This is what Andrew Ng draws in his pooling layers video in the Coursera Deep Learning Specialization: and this is what he draws in Inception network video: Notice in first slide, number of input ...
1 vote
1 answer
3k views

ValueError: cannot reshape array of size 36276416 into shape (96,227,227,1)

I am running my LeNet code with LFW, but when I run it, I am getting the following error message: Here is the code that it is getting the error ...
1 vote
1 answer
128 views

Transfer learning with many small datasets

Context I am working on a NLP-model that can classify documents into one of N categories. I have document data from a number of different customers. The document topics are similar across customers ...
0 votes
1 answer
386 views

When will the mlp give constant prediction?

I have a regression task (to predict price for finanical market.) I build a mlp to do the regression. I found mlp will stop at giving a constant prediction, which i think it's useless. Does this mean, ...
2 votes
2 answers
368 views

How to implement Semantic Search in R or Python

I have a task to provide semantic searching capabilities. For example, if I have a dataset of resume and if I search for "machine learning" than it should return me all resumes which have data science-...
0 votes
1 answer
14 views

Understanding batching in pytorch models

I have following model which forms one of the step in my overall model pipeline: ...
2 votes
1 answer
2k views

While retraining a pretrained model, getting: ValueError: Input 0 is incompatible with layer flatten_1: expected min_ndim=3, found ndim=2

My model summary is: ...
0 votes
0 answers
27 views

Extremely Imbalanced and Gapped Dataset in Regression Problem

Currently I am working with a biological dataset with a range of 0-to-1 to do a multi-task regression with Deep Learning. However, this dataset has an empty gap in the range 0 to 0.2 (however there ...
1 vote
1 answer
475 views

Computing variance of an SGD iteration

It is known that SGD iteration has huge variance. Given the iteration update: $$ w^{k+1} := w^k - \underbrace{\alpha \ g_i(w^k)}_{p^k}, $$ where $w$ are model weights and $g_i(w^k)$ is gradient of ...
0 votes
2 answers
943 views

Is plant classes or any crop is present in Imagenet datasets?

I am working on a project, which is based on plants. I only want to know that whether Imagenet datasets include tree, crop classes or not.
0 votes
0 answers
18 views

Create model for manufacturing defect detection using python

Has anyone done some work on manufacturer defect detection? I need some input on this. I have done some research and found some examples like TensorFlow/Keras and CNN, but I need some real-time ...
1 vote
1 answer
4k views

Keras: ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=2

I am using Keras functional API to write an LSTM model but It throwing an error can somebody please help below is the code for the model the output shape is 65. I am using Keras 2.2.4 and TensorFlow 1....
1 vote
1 answer
506 views

Does anybody know where this rule of thumb came from? Rule of them: embedding vector dimension should be the 4th root of the number of categories

I was taking an online ML course and the lecturer said that a rule of thumb for choosing the number of dimensions when embedding categorical data is the following ...
0 votes
0 answers
12 views

Trying to understand Ch.2.1 "2.1. Monads and their algebras" of "Categorical Deep Learning: An Algebraic Theory of Architectures"

I am trying to read article "Categorical Deep Learning: An Algebraic Theory of Architectures" https://arxiv.org/abs/2402.15332 and I am stuck with the Chapter 2.1 "2.1. Monads and their ...
0 votes
0 answers
8 views

Resources for writing CNN for semantic segmentation

I am intermediate/advanced in Python and new to machine learning. Most of what I know about deep learning I learned through Deep Learning with Python by François Chollet. I am trying to do image ...
2 votes
1 answer
291 views

Intuition: why are ReLu activations boundary lines linear?

What is the reasoning behind ReLu boundary lines appearing linear when plotting in 2D? Does this generalize to higher dimensions in that boundary lines in large dimensions are linear hyperplanes as ...
0 votes
1 answer
306 views

while re-training a pre-trained model, I'm facing this issue RuntimeError: You must compile your model before using it

model summary: RuntimeError: You must compile your model before using it. It says that the model needs to be compiled. But as far i know, if i compile a model, all the previous trained data will be ...
1 vote
2 answers
114 views

Implementing training in PyTorch

I wish to accomplish the following task in PyTorch- I have the COCO dataset, wherein each data sample is used in training YOLO v3. After being processed by the model, the sample is to be deleted if ...
0 votes
1 answer
503 views

How to find the class name of a new image from the pre-trained model

I would just like to get the class names of the predictions. I can get the class names on the images that I trained the model. But if I predict an image (say which is not trained but already belongs ...
1 vote
1 answer
484 views

Handling a large dataset consisting of npy files

I have a high number of npy files (448 files) each consisting of around 12k frames (150x150 RGB images) which together make the input to my neural network (X). However, since it is impossible to load ...
0 votes
0 answers
8 views

DCGAN for mammograms

I'm currently working on a DCGAN with Wasserstein Distance Gradient Penalty (WGAN-GP) for mammograms. The target mammograms are in 4D, as I'm using SD VAE 1.4 to reduce the complexity. Each of the ...
0 votes
0 answers
7 views

MIT-BIH and ECG-ID for ECG Authentication System

Both the MIT-BIH and ECG-ID data files are stored in the Waveform Database (WFDB) file format. The record_name.dat file formats are binary files containing samples of digitized signals. So, can I ...
1 vote
0 answers
25 views

Are formulas in the article incorrect?

I am learning about backpropagation in LSTM. I have been studying an article and watching two videos on the topic. The videos 1 and 2 repeat all the information from the article, but with additional ...
1 vote
1 answer
26 views

Best modelling method when target is a distribution

I have a regression task where each data sample is annotated by multiple (5-10) experts. I observe that the annotated target of each data sample is a Gaussian distribution. Usually, people will use ...
0 votes
1 answer
18 views

can we use tanh activation function to detect outliers?

Can we use tanh activation function to detect outliers ? Does my image below true for dataset outliers (after training model with tanh activation function) ?
1 vote
2 answers
1k views

Trying to convert a .txt file into .npy file to split and use for train/validation/test

I have a large data set in .txt form, and was trying to split it into three for testing, validation, and training by transforming the data into a ...
4 votes
0 answers
62 views

Why did I got opposite results of the original "How transferable are features in deep neural networks" paper?

I got tasked with reproducing the results of the influential "How transferable are features in deep neural networks?" paper in a DL class I'm taking (Full code). I got the exact opposite ...
0 votes
2 answers
4k views

Loss of NAN, Accuracy of 0 - Any idea why? Full code provided

I've been on this for the past few days and couldn't figure it out. Posted on various groups, StackOverflow etc and got suggestions from many users. I implemented these suggestions into the code shown ...
1 vote
2 answers
997 views

Can siamese model trained with euclidean distance as distance metric use cosine similarity during inference?

If I have 3 embeddings Anchor, Positive, Negative from a Siamese model trained with Euclidean distance as distance metric for triplet loss. During inference can ...

1 2 3
4
5
98