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
6 views

Deep learning based physics engine

Ridgid body simulation is a well known field with well established methods. It's still fairly computationally expensive to simulate things. I am interested in approaches to training deep learning ...
0
votes
0answers
4 views

Need some help in understanding a Research paper on Auto Image Colorization

I am having trouble understanding implementation of a research paper. Paper I need assistance in the 3.6 Final Classification Model on page 3. How exactly should the pixels be discretized into 50 bins?...
0
votes
0answers
10 views

Does replacing 3x3 filters with 3x1 and 1x3 filters improve the performance?

Recently I have come up with a VGG16 model for my binary classification task. I have relatively simple signal images Therefore (maybe?) other deeper models like ...
0
votes
0answers
15 views

What are some good models to use for spelling corrections?

I used OCR to extract text from an image, but there are some spelling mistakes in it : The text is as follows : ...
0
votes
0answers
12 views

How to use SPP-net and what are its drawbacks?

I read about the spatial pyramid pooling concept, it's really cool! Now, my doubt is how to find the number of layers to use, and in each layer what should be the grid sizes when using spp. But, I ...
1
vote
0answers
32 views

Which loss function to choose for imbalanced datasets?

For imbalanced datasets (either in the context of computer vision or NLP), from what I learned, it is good to use a weighted log loss. However, in competitions, the people who are in top positions are ...
2
votes
0answers
28 views

Enforcing sparsity constraints that make use of spatial contiguity

I have a deep learning network that outputs grayscale image reconstructions. In addition to good reconstruction performance (measured through mean squared error or some other measure like psnr), I ...
1
vote
1answer
30 views

Does it make sense to train images (for object detection algorithms) with cameras that will not be used to collect future data?

I am training an algorithm to identify weeds within crops using the YOLOv5 algorithm. This algorithm will be used in the future to identify weeds in images collected by unmanned aircraft (drones) ...
1
vote
1answer
18 views

Back propagation approach to logistic regression: why is cost diverging but accuracy increasing?

Background I have tried to fit a logistic regression model - written using a forward / back propagation approach (as part of Andrew Ng's deep learning course) - to a very non-linear data set (see ...
1
vote
0answers
18 views

Duplicating calculations in CNN-LSTM architecture

I want to use frames from video game and analyze them using CNN and LSTM. But when I have the model defined like that ...
1
vote
0answers
47 views

How differentiable programming and programming language supporting it will potentially help the development towards AGI?

After the state of the art Deep Learning techniques/algorithms being implemented in low-level languages like Objective-C, C++, etc to high-level languages like Python, JS, etc. and with the help of ...
0
votes
0answers
8 views

DirectoryIterator' object has no attribute '_variant_tensor' [migrated]

I am working through a tensorflow tutorial to get clued up on using pretrained models and ran into the error "DirectoryIterator' object has no attribute '_variant_tensor'" I am trying to ...
0
votes
1answer
21 views

Can a neural network be trained on a dataset containing only values for true output for a classification problem?

I am using a dataset from Google which contains 1,27,000 data points on simulated concentrations of the atmosphere of exoplanets which can sustain life. So, the output label of all these data points ...
0
votes
2answers
40 views

How do I label images for deep learning classification?

I have roughly 30,000 images of two categories, which are 'crops' and 'weeds.' An example of what I have can be found below: The goal will use my training images to detect weeds among crops, given an ...
0
votes
0answers
38 views

Is continuous learning possible for a deep neural network (without changing its topology)?

Is continuous learning possible for a deep neural network? Is it possible without fundamentally changing the network topology? This is a theoretical question. I have a trained network for which the ...
1
vote
2answers
37 views

Extract features with CNN and pass as sequence to RNN

I read an article about captioning videos https://blog.coast.ai/five-video-classification-methods-implemented-in-keras-and-tensorflow-99cad29cc0b5 and I want to use solution number 4 (extract features ...
0
votes
1answer
24 views

Zero shot learning available labels in testing set

As we all know, zero shot learning involves a model predicting classes that it has not seen. But we are given all the attributes each class might have. Is it fair to assume that we are "aware&...
0
votes
1answer
24 views

How to use a NN for seq2seq tasks?

I am trying to make a NN(probably with dense layers) to map a specific input to a specific output (or basically sequence2sequence). I want the model to learn the relation between the sequences and ...
0
votes
0answers
16 views

Strategy to input and get large images in VGG neural networks

I'm using a transfert-style based deep learning approach that use VGG (neural network). The latter works well with images of small size (512x512pixels), however it provides distorted results when ...
-2
votes
0answers
63 views

How do I write the architecture (layers, activation functions, etc.) of a neural network in pseudocode?

I am looking to convert a CNN model written in Python (keras) to pseudocode. I am mostly trying to find out the logic on how to describe the layers, the filters, the activation functions etc in ...
0
votes
0answers
13 views

Is there a model suitable to predict one correct value based on a 2D input series?

I am using an encoder-decoder architecture, with 2 layers each in the encoder and decoder and 128 neurons in each hidden layer. The inputs are in a 2D form: one column has the days and the other ...
1
vote
0answers
38 views

Is there any way where you can train a Neural Network with only one data point in the dataset?

I was working on a project involving the search for biosignatures (signs of life) on exoplanets and the probability of that planet harboring life. In this case, we know that Earth is the only planet ...
0
votes
0answers
23 views

Confusion on Math Notation Definition

I attempt to understand the formulation of dictionary learning for this paper: Depression Detection via Harvesting Social Media: A Multimodal Dictionary Learning Solution Multimodal Task-Driven ...
2
votes
0answers
14 views

Is regular/offline gradient descent ANN training equivalent to “rehearsal” in incremental learning?

I am self-learning incremental learning and read that rehearsal learning is retraining with old data. In essence, isn't this the exact same thing as normal batch/stochastic gradient descent? You train ...
2
votes
2answers
134 views

How to identify if 2 faces contain the same person?

I have got numerous frames and I've detected all the faces in all the frames using Retinaface. However I need to track the faces of people over frames. For this purpose, I assumed I could try finding ...
0
votes
0answers
11 views

CuPy CUDA error in Chainer [migrated]

I am running SSD300 model in Chainer for object detection. The GPU is GeForce 2080 RTX Ti. While training after n number of epochs the training fails. It throws the following error: ...
2
votes
0answers
27 views

Handling a Large Discrete Action Space in Deep Q Learning

I am attempting to solve a timetabling problem using deep Q learning. It could be thought of as a resource allocation problem to obtain some certificate of 'optimality'. However, how to define and ...
0
votes
0answers
37 views

What prerequisite knowledge should I have to learn about neuromorphic chips and computing?

What prerequisite knowledge should I have and what are the best resources to learn about neuromorphic chips/computing on a deep, technical level? I would like to understand everything from the ...
0
votes
1answer
26 views

What is the dimension of my output of the form (2n + 1, 2n + 1, #filters) after a MaxPooling layer

I'm trying to white board the different mechanisms behind a convolutional neural network. I have on question regarding the dimension of my volume after using a max pooling layer. Let's suppose I have ...
2
votes
1answer
41 views

Why does using a higher representation space lead to performance increase on the training data but not on the test data?

I read the following from a book: You can intuitively understand the dimensionality of your representation space as “how much freedom you’re allowing the model to have when learning internal ...
0
votes
0answers
17 views

Calculating processing time of a deep learning model

My model deals with videos, and I want to calculate how fast it can process frames as in frames per second or processing time for 1 frame. I have made a single function to get predictions, it takes in ...
0
votes
0answers
20 views

How can I calibrate 3 cameras and track the object using only synchronized cameras feeds from all the cameras?

I have camera feed (in the form of RGB images) from 3 cameras with partially overlapping Field-of-view i.e. for the time stamp 0 to 100, I have total 300 frames or say synchronized 100 RGB frames for ...
1
vote
1answer
46 views

How to calculate the GPU memory need to run a deep learning network?

In general, how do I calculate the GPU memory need to run a deep learning network? I'm asking this question because my training for some network configuration is getting out of memory. If the ...
2
votes
0answers
19 views

How is the data labelled in order to train a region proposal network?

I don't get how the training of the RPN works. From the forward propagation, I have $W \times H \times k$ outputs from the RPN. How is the training data labeled such that I can use the loss function ...
3
votes
1answer
57 views

How can I fix jerky movement in a continuous action space

I am training an agent to do object avoidance. The agent has control over its steering angle and its speed. The steering angle and speed are normalized in a $[−1,1]$ range, where the sign encodes ...
2
votes
1answer
63 views

Why is sampling non-uniformly from the replay memory an issue? (Prioritized experience replay)

I can't seem to understand why we need importance sampling in prioritized experience replay (PER). The authors of the paper write on page 5: The estimation of the expected value with stochastic ...
0
votes
1answer
41 views

What type of model should I fit to increase accuracy?

Currently, I'm working on 6-axis IMU(Inertial Measurment Unit) dataset. This dataset contain 6 axis IMU data of 7 different drivers. The Imu sensor attached on vehicle. The drivers drives same path. ...
1
vote
1answer
30 views

How classification neural nets are different from simple dimension reduction + clustering?

I know the training of neural nets involves some sort of dimension manipulation to separate classes of different features. If there is no variation of features, no matter for neural nets or simple ...
0
votes
0answers
19 views

Logistic Regression or General Machine Learning Model using Federated Learning

Past few days I am doing some research on Federated Learning. I got many solutions with MNIST dataset using Nural Net but I am thinking to solve some common Machine Learning problem like Churn ...
0
votes
0answers
26 views

Keeping track of multiple faces throughout a video

I have a video where multiple persons are seated. I need to keep track of the emotions they show throughout the video. My final result should be a csv file with all the emotions depicted by each ...
1
vote
1answer
32 views

Deep Reinforcement Learning Atari: how does the agent understand motion?

Basic deep reinforcement learning methods use as input an image for the current state, do some convolutions on that image, apply some reinforcement learning algorithm and it is solved. Let us take the ...
0
votes
0answers
11 views

Working of embedding layer in Tensorflow [migrated]

Can someone please explain me the inputs and outputs along with the working of the layer mentioned below ...
1
vote
1answer
38 views

How is exponential moving average computed in deep Q networks?

In normal Q-learning, the update rule is an implementation of the exponential moving average, which then converges to the optimal true Q values. However, looking at DQN, how exactly is the exponential ...
2
votes
0answers
21 views

Combine DQN with the Average Reward setting

I have to deal with a non-episodic task, where there is addittionally a continuous state space and more specifically in each time step there is always a new state that has never been seen before. I ...
1
vote
1answer
22 views

How is weighted average computed in Deep Q networks

I was going through the Sutton book and they said the update formula for Q learning comes from the weighted average of the returns I.e New estimate= old estimate +alpha*[returns- old estimate] So by ...
0
votes
0answers
26 views

Structure for neural network

My purpose is to apply deep learning for planning. To do so, I decided to use a similar approach as AlphaGo. But my "game state" is very different. Instead of considering some planes ...
0
votes
0answers
18 views

Should I move on from R and use Python for AI? [duplicate]

I have been using RStudio for a few years now, for various machine learning and deep learning techniques. For example, I want to build a trading bot that takes into account live news, which is tougher ...
0
votes
1answer
23 views

How to train the images of various sizes?

I am practicing with an image dataset which is having different dimensions. If I simply crop and pad them to 1024X1024(the original images having smallest width is around 300 and largest is around ...
2
votes
1answer
31 views

Why is the mean used to compute the expectation in the GAN loss?

From Goodfellow et al. (2014), we have the adversarial loss: $$ \min_G \, \max_D V (D, G) = \mathbb{E}_{x∼p_{data}(x)} \, [\log \, D(x)] \\ \quad\quad\quad\quad\quad\quad\quad + \, \mathbb{E}_{z∼p_z(...
0
votes
0answers
14 views

How can I decrease the time to compute the mask in the Mask-RCNN for human body detection?

I am using Mask-RCNN to detect human bodies in photos, to get a rough approximation of the ratio of their heights to the length of their chests. I want to decrease the time for making the mask of the ...

1
2 3 4 5
27