Questions tagged [deep-learning]

For questions related to deep learning, which refers to a subset of machine learning methods based on artificial neural networks (ANNs) with multiple hidden layers. The adjective deep thus refers to the number of layers of the ANNs. The expression deep learning was apparently introduced (although not in the context of machine learning or ANNs) in 1986 by Rina Dechter in the paper "Learning while searching in constraint-satisfaction-problems".

Filter by
Sorted by
Tagged with
0
votes
0answers
3 views

How can I get the images with the highest activation for a given unit?

I am new to machine learning. I am working on the pretrained AlexNet on Pytorch and i would like to visualize the receptive fields of a given unit U. To do that I am trying to give like 200K images as ...
0
votes
0answers
5 views

Bounding box transformation using point cloud

I am working on a project in which I have an RGB Image and the corresponding 2d bounding boxes for the objects in the image. I also have a respective point cloud and therefore, I can extract the depth ...
0
votes
0answers
12 views

Exctracting features fro image captioning

If I want to do image captioning on a datasets, what are the steps I need to do that if I'm using object detection model? Should I freeze layers or not? The steps in my mind are Get the features from ...
1
vote
0answers
4 views

DeepLabV3: Why use global average pooling in the ASPP module?

I'm trying to understand the rationale of the various modifications the authors of the DeepLab models have made to their third version, DeepLabV3. In the paper, the following is written: ASPP with ...
1
vote
0answers
9 views

Finetuning solver for Caffe neural network

We're working on object detection in thermal images using neural network with Caffe framework. We use SSD ResNet-10 network available in OpenCV repository as it seems to provide the best performance ...
1
vote
1answer
36 views

Would this count as a Transfer Learning approach?

I have two datasets, Dataset 1(D1) and Dataset 2(D2). D1 has around 22000 samples, and D2 has around 8000 samples. What I am doing is that I train a Deep Neural Network model with around three layers ...
1
vote
0answers
21 views

Identifying rotating and resizing letters with background noise

I'm trying to complete a certain type of captcha for academic purposes. Here is what it looks like: Between captchas the calligraphy of the letters is the same, but the letters may be resized and ...
1
vote
0answers
14 views

What is the best way to train neural network with imbalanced mixed data (images and structured data)?

I have structured data and image data to solve a regression problem. One sample of structured data can be related to N images. If I use only structured data, I get decent performance, but not enough ...
1
vote
0answers
10 views

CFD Reinforcement Learning Topology optimization wind tunnel

I want to create a reinforcement learning environment, designed for win tunnel simulations, where for each iteration a deep convolutional model could receive the 3D vector/scalar fields from the past ...
1
vote
1answer
15 views

What to do when you have massive amount of data but you don't have enough computation power for training a machine learning model?

For example, I have a massive amount of data, but I have limited computational resources and time to train on the full data. Other cases may include, I have huge amounts of 360-degree images, where I ...
0
votes
0answers
9 views

How to use Tensorflow Recommenders' Retrieval task with Keras data generators

I've recently started working with the package to build recommender systems, and so far, I've successfully built a Ranking task that takes the inputs from a Keras Data Generator. However, I could not ...
0
votes
0answers
11 views

Why the collection of background/negative image dataset is not taught in object detection tutorials and books?

While I was doing an object detection project, I have encountered the problem of getting FALSE POSITIVES and FALSE NEGATIVES. After days of research on StackOverflow, I figured out that I need to ...
0
votes
0answers
43 views

Is it possible to mimic someone's handwriting given their sample notes?

I have a pet project, but I'm not very well versed with AI. I posted this question on datascience.stackexchange with no luck. I think this forum is more apt, so can anyone here help me start this in ...
1
vote
4answers
90 views

How much statistics is involved in AI?

This may be a stupid question but I couldn't really find an answer on the internet. I am a 3rd year math major who is interested in computer science, particularly algorithms and competitive ...
0
votes
0answers
8 views

How to measure(classify) the speed of oncoming traffic via Computer Vision and Neural Networks?

Suppose I have different videos of the same car sometimes moving slow, sometimes moving fast, say, at 50Kmph as slow and 60Kmph as fast. (Assume the background is a green screen and the car doesn't ...
0
votes
1answer
21 views

What is the difference between feature extraction and fine-tuning in transfer learning?

I'm building a model for facial expression recognition, and I want to use transfer learning. From what I understand, there are different steps to do it. The first is the feature extraction and the ...
0
votes
1answer
19 views

Changing a CNN-LSTM image captioning architecture to use BiLSTMs

Currently I'm dealing with an assignment that made us implement the network mentioned in this paper. The network has an architecture similar to this: As you can see it uses a Unidirectional RNN (in ...
1
vote
0answers
27 views

How to learn transition type in a 1-hour extended DJ Mix?

How would you design a model which learns the transitions in a given 1-hour DJ Mix? To be specific, the model should be able to learn transitions, specify the occurring time and the type (Crossfade, ...
0
votes
0answers
20 views

How to remember previously detected objects in computer vision?

Let's say I have a drone that has to fly (and scan) over some area (blue on the images - in this case a PV power plant, but it could be anything) in an autonomous way like in the pic below: Let's ...
0
votes
0answers
23 views

How do autoregressive attention mechanism work in multi-headed attention?

[LONG POST!!] I am working on a DNN model that works as an improviser to generate music sequences. The idea of generating music is based on taking a sequence of music nodes (their index representation)...
0
votes
0answers
17 views

Image regression - estimating sensors from images

I am trying to use images to predict the sensor data of a racing game. Being a bit of a newcomer I have multiple questions. All help/suggestion is appreciated. Dataset The dataset looks something like:...
0
votes
0answers
16 views

Neural Networks different architectures but similar training curves

I have a base neural network architecture for (3D) image sequences classification, made of conv layers followed by a LSTM and dense layers. I have 3 similar architectures : 3 Conv -> 1 LSTM -> ...
4
votes
1answer
40 views

In the field of Deep Learning research, what considerations do researchers take into account when inventing new neural network models?

I am not a researcher, but I am curious to know what considerations are relevant to take into account during research for the invention of a new neural network model, and what relevant knowledge ...
0
votes
0answers
11 views

What does it mean when predicted results are constant values?

I'm practicing with some data with a LSTM neural nets to come up with predicted data, comparing with actual data. I generated an image to show what I came up with. The blue line is actual data, and ...
0
votes
1answer
27 views

Is there a performace benefits using VAE-GAN instead of just GAN?

I have read that when using VAE-GANs, first what happens is the VAE's encoder encodes some image to another encoded image, which from GAN's point of view is considered a noise, and then the GAN part ...
0
votes
0answers
25 views

Weird KL divergence behaviour

I'm training a complex model for motion prediction using a VAE, however the KL divergence has a very strange behavior. A scheleton of the network is the following: At the end my network compute the ...
1
vote
1answer
24 views

What is meant by “stable training” of a deep learning model?

I have read it said that the "stable training" of a deep learning model is important. What is meant by "stable training" of a deep learning model?
1
vote
1answer
32 views

Why is the validation loss less than the training loss, and what can be said about the effect of the learning rate?

I have the following results I am trying to make sense of. I have attached the loss curves here for reference. As you can see, the first issue is that the validation loss is lower than the training ...
0
votes
1answer
33 views

What makes a transformer a transformer?

Transformers are modified heavily in recent research. But what exactly makes a transformer a transformer? What is the core part of a transformer? Is it the self-attention or the parallelism or ...
0
votes
0answers
17 views

How to retrain Facenet model?

I want to calculate the similarity or distance of two faces, and I'm using python. I have read and do what this tutorial says. but the result is not good (the similarity of same faces and similarity ...
0
votes
0answers
6 views

Arcface implementation for image similarity produces opposite embeddings for positive negative image pairs

So I've built an arcface model with this arcface layer implementation: https://github.com/4uiiurz1/keras-arcface/blob/master/metrics.py I trained for a few epochs and now that I'm comparing the ...
2
votes
1answer
68 views

Do we ever need more then 1 hidden layer in a binary classification problem with ANNs? If yes why?

I have read about the universal approximation theorem. So, why do we need more than 1 layer? Is it somehow computationally efficient to add layers instead of more neurons in the hidden layer?
0
votes
0answers
19 views

How to improve the Loss and Learning curves and smoothen them

I am fairly new to deep learning and I have been testing out several architectures for the segmentation task of clouds in satellite imagery. I am using a simple Unet as my benchmark, Unet++, Efficient ...
0
votes
0answers
9 views

how to use Laplacian of mesh structure (LBO) for meshes that are registered in deep learning methods based on spectrum (ChebNet for isntance)?

In graph neural network frameworks, there is always a template with a shared structure among all graphs. I have meshes that are registered but obviously, Lalpalcian and their geometry are different. ...
1
vote
0answers
146 views

Convolutional Layer Multichannel Backpropagation Implementation

I have been working on coding a CNN in python from scratch using numpy as a semester project and I think I have successfully implemented it up to backpropagation in the MaxPool Layers. However, my ...
0
votes
0answers
22 views

Task/Process Scheduling Using DQN: Agent Does Not Learn

I have a problem statement where a couple of smartphones, for example inside a shopping mall, can migrate their time-consuming tasks/processes like image processing to an edge server located nearby. ...
0
votes
2answers
52 views

What is the process working on Tensorflow model.fit()? [closed]

I created a binary image classification model. The dataset contains about 500K images in each class, with ratio = Train : Validation : Test = 7 : 2 : 1. Total images = 1M I split my dataset into 5 ...
2
votes
0answers
15 views

Predicting the the motion of a 3D object when the motion of a set of markers is known

trying to figure out where to get started with this: I have a few hundred CT images where certain three-dimensional features in the image (anatomy) are moving in a correlated fashion with a set of ...
0
votes
0answers
7 views

How can we use Deep Learning for Faults Tolerence in Distributed System?

Cloud Computing is the best example of Distributed Systems. The devices or nodes used in Distributed Systems consume and produce Big Datas, Hence there are chances of fault occurence from any end ...
0
votes
2answers
58 views

Unet Overfitting for binary segmentation of fake images

I am working on a project where I am trying to detect and localize forgeries in images. I am using the CASIA v2 dataset and using Unet model for the task. I have the binary masks of all the images in ...
1
vote
0answers
27 views

Construction of GRUcell using Tensorflow to get the hidden states [closed]

I want to construct a GRU cell with one hidden layer but I want to get the hidden states at each time step. I want to train the GRU cell for let's say 10 times and at every step to get the hidden ...
3
votes
0answers
40 views

Why might the convolution be inappropriate when the task involves incorporating information from very distant locations in the input?

When I am reading about convolutional neural networks, I have encountered the following sentence from the textbook(page 341) that says about the limitation of the usage of the convolution in CNNs. ...
0
votes
0answers
17 views

Is there a different approach, other than MAML combined with LSTM, for meta-regression of time-series data?

I am working on the calibration of low-cost air sensor data (a time series regression problem). My primary focus is to use some meta/ few-shot learning approach to solve this problem with fewer data. ...
0
votes
0answers
37 views

How is it possible that the softmax combined with the MSE in a molecule classification task performs than than the cross-entropy?

I'm working on a GNN project associated with molecule classification. The project is to classify if the atom in the molecule will initiate a certain reaction. For example, a molecule can be ...
0
votes
0answers
23 views

Reward firstly increase, but after more episodes, start decrease, and weights diverges

I'm making a simple deep Q learning algorithm, with cartpole-v1 env. Like you can see in chart, after many episodes the reward decrease, some possible reasons? The exploration vs axplotation algorithm ...
1
vote
1answer
27 views

Why are weights not initialized with mean=1?

I wonder why weights are initialized with zero-mean. It is one of the reasons, why deep architectures cannot be trained without skip connections. Without the skip connections, the zero initialization ...
1
vote
0answers
15 views

Why does Adam optimizer work slower than Adagrad, Adadelta, and SGD for Neural Collaborative Filtering (NCF)?

I've been working on Neural Collaborative Filtering (NCF) recently to build a recommender system using Tensorflow Recommenders. Doing some hyperparameter tuning with different optimizers available in ...
1
vote
2answers
40 views

What is the difference between applying shallow-learning methods repeatedly and deep learning?

In the book Deep Learning with Python, François Chollet writes (section 1.2.6, page 18) In practice, there are fast-diminishing returns to successive applications of shallow-learning methods, because ...
0
votes
0answers
9 views

Choosing the size of the network for Neural Collaborative Filtering (NCF)?

I've been working on Neural Collaborative Filtering (NCF) recently to build a recommender system. After doing some hyperparameter tuning with various sizes for embedding and dense layers sizes, from ...
0
votes
0answers
10 views

Can I get some advices on inferencing people from upwards using Yolov5?

I'm trying to inference people from upwards and count them using Yolov5. I know the controversy between yolov5 and yolov4, but for me, Yolov5 is more easier and reliable to use, also the setup. I have ...

1
2 3 4 5
32