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
7 views

Importance of Decoder in Capsule Network

Capsule Networks use an encoder-decoder structure, where the encoder part consists of the capsule layers (PrimiaryCaps and DigitCaps) and is also the part of the capsule network which performs the ...
0
votes
0answers
14 views

How can we derive a Convolution Neural Network from a more generic Graph Neural Network?

Convolution Neural Network (CNNs) operate over strict grid-like structures ($M \times N \times C$ images), whereas Graph Neural Networks (GNNs) can operate over all-flexible graphs, with an undefined ...
1
vote
2answers
41 views

Why is my Keras prediction always close to 100% for one image class?

I am using Keras (on top of TF 2.3) to train an image classifier. In some cases I have more than two classes, but often there are just two classes (either "good" or "bad"). I am ...
1
vote
1answer
31 views

What are the conceptual differences between regularisation and optimisation in deep neural nets?

I'm trying to wrap my mind around the concepts of regularisation and optimisation in neural nets, especially around their differences. In my current understanding, regularisation is intended to tackle ...
1
vote
0answers
14 views

Object Detection as a means of Anomaly Detection

Is it possible to train an Object Detector (e.g. SSD), to detect when something is not in the image. Imagine an assembly line that transports some objects. Each object needs to have 5 screws. If the ...
1
vote
0answers
88 views

How should I build this DQN agent?

I have a set of users that can be one of 3 types. They will randomly request a service from the UAV which is a drone used as a Base Station. The UAV (the agent) is tasked with allocating subchannels (...
0
votes
0answers
26 views

How to generate a matrix out of sparse data?

I have a system that takes 32 inputs (all of which are 1 or 0) and generates 32 outputs (all of which are complex numbers that lie roughly in the range of (0,2)). The response of this system to its ...
-1
votes
0answers
25 views

computational complexity of attention in dynamic-convolution

I'm reading this paper , Dynamic convolution-Attention over Convolution kernels. I couldn't understand the complexity of attention i.e., How to calculate O(π(...
0
votes
1answer
20 views

Semantic segmentation failing in small instance detection

I performed semantic segmentation with U-net. My dataset consists of grayscale images of defects. After training the dataset for I got an metric accuracy of only 0.3 - 0.4 IOU. Eventhough it is merely ...
-1
votes
0answers
17 views

Find the distance between two objects from a 45 degree tilted camera images taken from a drone with a specific elevation from the ground

I have a project where i'm supposed to find the distance and the height of a specific object in an image taken by a drone using one camera. I have looked into perspective transformation/correction but ...
2
votes
1answer
22 views

Does this diagram represent several LSTMs, or one through several timesteps?

I'm trying to read this paper describing Google's LSTM architecture for machine translation. It features this diagram on page 4: I'm interested in the encoder block, on the left. Apparently, the pink ...
0
votes
0answers
25 views

What is the purpose of soft orthogonal regularization in training deep neural network?

I'm reading papers regarding soft orthogonal regularization, $\frac \lambda 4||WW^\intercal - I||_F^2$, over a deep neural network whose activation function is ReLU and weight matrix $W$ is ...
1
vote
1answer
34 views

Why are shallow networks so prevalent in RL?

In deep learning, using more layers in a neural network adds the capacity to capture more features. In most RL papers, their experiments use a 2 layer neural network. Learning to Reset, Constrained ...
0
votes
0answers
21 views

How does Google's 2016 GNMT architecture work?

I'm trying to read this paper describing Google's LSTM architecture for machine translation from 2016. However, I'm getting stuck as certain things are described too vaguely for me. This is a picture ...
1
vote
1answer
21 views

Predict next event based on previous events and discrete reward values

Suppose, I have several sequences that include a series of text (the length of sequence can be varied). Also, I have some related reward value. however, the value is not continuous like the text. It ...
0
votes
0answers
9 views

What Deep Learning Applications Might Require Super-Computers or “SuperPODs”

With the release of NVIDIA's DGX SuperPOD of A100 GPUs, supercomputers will/are becoming more and more common-place. What potential deep learning tasks/applications might become more accessible with ...
1
vote
0answers
24 views

How is input defined for a biaxial lstm network for generating music?

I am reading Composing Music With Recurrent Neural Networks by Daniel D. Johnson. But I am really confused about the input passed to this network. If we pass notes of music along the time axis, then ...
0
votes
0answers
4 views

In a face database containing multiple images per subject, how do we determine the face image which is most suited for face recognition?

Let us imagine a face database with several subjects, each subject having multiple face images. How do we determine which is the best face suitable for face recognition purposes?
0
votes
0answers
7 views

Best strategy for Classification of Science Subjects. Phy, Chem , Maths and Bio? BERT, Transformers, Attention+SLTM, Self-Attention+LSTM?

I am working on a project where I have to first classify the Subjects of the given question and then the respective Chapter and then the sub-topic. In a nutshell, I have to predict the Subject, Grade ...
0
votes
0answers
24 views

Reference for Yoshua Bengio quote

I believe that Bengio is on record as describing Deep Learning as "A collection of methods for delivering intelligence" (or something very similar). Does anyone have an actual reference for ...
2
votes
0answers
21 views

If random rotations are included in the data augmentation process, how are the new bounding boxes calculated?

When studying bounding box-based detectors, it's not clear to me if data augmentation includes adding random rotations. If random rotations are added, how is the new bounding box calculated?
0
votes
0answers
18 views

Am I using transfer learning when I use SSD ResNet 50 model architecture?

Using Label-img, I have successfully labeled my images (dimensions 1100 x 1100 pixels), and am currently training the SSD ResNet50 model (from the TensorFlow 2 Detection Model Zoo). I downloaded the ...
1
vote
1answer
32 views

DQN layers when state space and action space are multi dimensional

I have built my own RL environment, where a state is composed of two elements: the agent's position and a matrix of 0s and 1s (1 if a user has requested a service from the agent, 0 otherwise); an ...
0
votes
0answers
11 views

Does a Siamese Network need other trainable layers after the distance layer?

I'm approaching at Siamese Networks in order to use them for Image Similarity. I found that many people use famous models like VGG or ResNet to build the vectors that will go on the distance layer in ...
1
vote
0answers
20 views

How can I improve the performance on unseen data for semantic segmentation using an auto-encoder?

I am using simple autoencoders for the task of semantic segmentation on the VOC2012 dataset. I am currently using a simple autoencoder based model. It is trained on adam optimizer with cross-entropy ...
2
votes
0answers
52 views

Why should the weight updates be proportional to input?

I'm reading the book Grokking Deep Learning. Regarding weight updates during training, it has the following code and explanation: ...
1
vote
0answers
38 views

Where can I find pre-trained agents able to play games with multiple stages like exploration, dialog, combat?

My goal is to create an ML model to be able to classify different game stages, e.g., dialog with a non-player character, exploration, combat with enemy, in-game menu etc. In order to do that, I am ...
1
vote
0answers
29 views

In the MINE paper, why is $\hat{G}_B$ biased, and how does the exponential moving average reduce the bias?

While reading the Mutual Information Neural Estimation (MINE) paper [1] I came across section 3.2 Correcting the bias from the stochastic gradients. The proposed method requires the computation of the ...
0
votes
0answers
36 views

How to determine the number of fully connected layers for a convolutional neural network?

How many fully connected layers should be added to a convolutional neural network? Does it depend on input size to the fully connected layer? If so, how do we decide? What if the input size of the ...
1
vote
0answers
21 views

When training deep learning models for object detection in images, do you need a large number of images, or a large number of training samples?

I am training a deep learning model for object detection. The consensus is that the more images that you have, the better the results will be. All the tutorials that I have seen say that more images ...
0
votes
0answers
16 views

CNN to detect presence/absense of label on images with mixed labels

Here's my problem: I work with medical image classification, and currently I have 3 classes: class A: images with lesion 1 only; and images with lesion 1 and N other lesions class B: images with 2 ...
0
votes
0answers
10 views

How does scheduled sampling for transformers work?

I was reading this paper which applies a modified version of the transformers for traffic forecasting. I am somewhat familiar with the transformer architecture and how it functions, but, in the paper, ...
1
vote
0answers
22 views

What is a “center loss”?

I have seen that a center loss is beneficial in computer vision, especially in face recognition. I have tried to understand this concept from the following material A Discriminative Feature Learning ...
1
vote
2answers
78 views

How to verify classification model trained on classification dataset on a detection dataset for classification purpose?

I am working on a problem that involves two tasks - detection and classification. There is no single dataset for both tasks. I am training two models, separate on detection dataset and another on ...
0
votes
0answers
14 views

Is there a way to import custom Reinforcement Learning Models into Unity? [migrated]

Unity provides two RL algorithms to train agents: PPO and SAC. I have been searching for weeks now on how to write my own algorithms and only found a mention of a gym-unity wrapper that wraps Unity ...
1
vote
0answers
19 views

What exactly are deep learning primitives?

I came across the concept of "deep learning primitives" from the Nvidia talk Jetson AGX Xavier New Era Autonomous Machines (on slide 44). There doesn't seem to be a lot of articles in the ...
1
vote
0answers
23 views

WGAN-GP Loss formalization

I have to write the formalization of the loss function of my network, built following the WGAN-GP model. The discriminator takes 3 consecutive images as input (such as 3 consecutive frames of a video) ...
0
votes
0answers
26 views

Is Webpage Semantic Segmentation possible nowadays?

I'm trying to do some research about semantic segmentation for webpages, in particular e-commerce webpages. I found some articles which provide some solutions based on very old dataset and those ...
0
votes
0answers
14 views

REINFORCE Agent suddenly drops. How to verify if it's due to catastrophic forgetting?

I am using the default implementations of REINFORCE, DQN and c51 available from the tf.agents repo (links). As you can see, DQN manages to improve performance while REINFORCE seems to suffer from ...
0
votes
0answers
8 views

Is there a framework or method that would help visualise inner workings of a feedforward neural network?

I wonder if there is some framework or method to help visualising inner workings of a feedforward deep neural network? What I mean by this is something similar to what is being done with CNNs where we ...
1
vote
1answer
44 views

Single-Shot Learning for Object Re-Identification

I am looking for a way to re-identify/classify/recognize x real life objects (x < 50) with a camera. Each object should be presented to the AI only once for learning and there's always only one of ...
0
votes
1answer
21 views

Should binary feature be in one or two columns in deep neural networks?

Let's assume I have a simple feedforward neural network whose input contains binary 0/1 features and output is also binary two classes. Is it better, worse or maybe totally indifferent, for every of ...
0
votes
0answers
24 views

How to use Deep Q-Network with two-dimensional input? Hands-on Machine Learning 2

I'm studying with the book Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow, and I'm trying to implement the Deep Q-Network example that can be found on Github but that the input ...
2
votes
1answer
28 views

Are there deep neural networks that have inputs connected with deeper hidden layers?

Are there any architectures of deep neural networks that connect input neurons not only with first hidden layer but also with deeper ones (red lines on the picture)? If so could you give some names ...
1
vote
0answers
29 views

What is the justification for Kaiming He initialization?

I've been trying to understand where the formulas for Xavier and Kaiming He initialization come from. My understanding is that these initialization schemes come from a desire to keep the gradients ...
1
vote
1answer
92 views

Applications of Information Theory in Machine Learning

How is information theory applied to machine learning, and in particular to deep learning, in practice? I'm more interested in concepts that yielded concrete innovations in ML, rather than theoretical ...
0
votes
0answers
42 views

Deep Learning based image restoration using multiple frames

Suppose we have a sequence of still images each of which has been contaminated by some particles(ex, dust/sand/smoke) making the images very poor in certain areas. What architecture would be best to ...
1
vote
1answer
33 views

What do we mean by “infrequent features”?

I am reading this blog post: https://ruder.io/optimizing-gradient-descent/index.html. In the section about AdaGrad, it says: It adapts the learning rate to the parameters, performing smaller updates (...
1
vote
1answer
68 views

How can I determine whether a video's frame is realistic (was recorded by a camera) or contains computer-generated graphics?

Given a video, I'm trying to classify whether it is a graphical (computer-generated) or realistic scene. For instance, if it contains computer-generated graphics, credit, moving bugs, blue screen, etc....
2
votes
2answers
229 views

How to tell a neural network that: “your i-th input is special”

Assume that I have a fully connected network that takes in a vector containing 1025 elements. First 1024 elements are related to ...

1
2 3 4 5
28