Skip to main content

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
24 views

Conv2d with time series

I have a question about how a CONV2D layer handles time series data. How with filters that scroll through time, our model can extract features and capture and model our target value? Thank you in ...
0 votes
1 answer
176 views

Should deep layers ever have more units than the input layer?

i.e. if a model, with 10 inputs, say,: ...
1 vote
1 answer
50 views

How to define similarity between nodes in original graph?

While there has been a lot of talk in how to define the similarity between nodes in the embedding space, but I don't seem to come across any talking about defining the similarity between nodes in the ...
2 votes
1 answer
349 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 ...
2 votes
1 answer
39 views

Noob question - which NLP/deep learning technique shoud I use

Let's say I have dataset with inputs and expected outputs like this: ...
1 vote
1 answer
51 views

How to add words to english model word list in Julius Speech Recognition Engine?

I want to add some English words to model but how can I achieve this ? https://github.com/julius-speech/julius
0 votes
1 answer
814 views

Keras CNN model is throwing as error message as 'ValueError: Layer 'conv1d_12' expected 2 variables, but received 0 variables during loading'

Hope you're in good health and doing great. I am trying to implement a CNN model to help predict kidney stones. Now, this model is running as expected on my local machine, but when I try deploying the ...
0 votes
0 answers
14 views

Semantics Building In LSTM-Based Models - How does a LSTM is able to extract and represent long data using just one value (long-memory)

How does a LSTM is able to extract and represent long sequences with data while using just one value (long-memory / LM) to maintain all this information? If multiple value were used, it could be ...
1 vote
2 answers
99 views

What is the typical things in Data that i have to look for, when implementing Survival Models using Machine Learning?

Problem Scenario I am working on an industry specific problem focussed on predicting the failure of a seal/gasket in the given time interval(T) in a high-pressure-compression environment. Whenever ...
1 vote
1 answer
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? <...
2 votes
1 answer
159 views

Dimensionality of the target for DQN agent training

From what I understand, a DQN agent has as many outputs as there are actions (for each state). If we consider a scalar state with 4 actions, that would mean that the DQN would have a 4 dimensional ...
1 vote
1 answer
170 views

why CNN model can't learn well the peak from data

here I have two different datasets. dataset1 is force plate data and dataset2 is plantar pressure data. dataset1 has shape (2050,2) and dataset2 has shape(2050,89). before doing the training I have ...
1 vote
1 answer
503 views

How to Use Multiple Adapters with a Pretrained Model in Hugging Face Transformers for Inference?

I have a pretrained Llama-2 model in the models_hf directory and two fine-tuned adapters: a summarization adapter in ...
3 votes
1 answer
533 views

How to train millions of doc2vec embeddings using GPU?

I am trying to train a doc2vec based on user browsing history (urls tagged to user_id). I use chainer deep learning framework. There are more than 20 millions (user_id and urls) of embeddings to ...
0 votes
0 answers
13 views

What are good configs for running UNet3DConditionModel on 8 GB VRAM? (64x64x64 inputs)

What are good configs for running UNet3DConditionModel on 8 GB VRAM? (64x64x64 inputs) More specifically for this project I'm looking to use HuggingFace's UNet3DConditionModel on my home PC on a RTX ...
0 votes
2 answers
52 views

CNN application assessment

I would be glad if someone could give me some hints and assessment for the following project. (I'm relatively new to ML and DL and having only a little theoretical knowledge) My goal is to build a ...
0 votes
1 answer
51 views

How big is the threshold that is usually used in determining the convergence of loss values in deep learning?

In deep learning, one way to determine whether the training has converged is to observe the movement of the loss values over iterations or epochs. One can choose any $\epsilon$ threshold and any ...
0 votes
1 answer
471 views

How to copy and crop feature map in Unet?

I am confused about the principle of copy and crop in U-net, like the grey line shown above. For example, the first grey line, how to convert a (64, 568, 568)(C,W,H) to a (128, 392, 392), did the ...
1 vote
1 answer
24 views

Linear warmup always result in a significant drop in accuracy

I'm at a machine learning task where I used linear warmup for a machine learning task. However, I observed that the test accuracy always drops significantly after the warmup, sometimes even during ...
1 vote
1 answer
53 views

Quantitative measure of the smoothness of learning curves

$\DeclareMathOperator{\loss}{loss}$ $\DeclareMathOperator{\AvgVar}{AvgVar}$ Lat's say we have some deep learning task. We have our model and two sets of hyperparameters $A$ and $B$. We train both ...
3 votes
1 answer
76 views

What's the best way to validate a rare event detection model during training?

When training a deep model for rare event detection (e.g. sound of an alarm in a home device audio stream), is it best to use a balanced validation set (50% alarm, 50% normal) to determine early ...
2 votes
1 answer
55 views

balancing and imbalancing in supervised anomaly detection probelm

I am dealing with a supervised anomaly detection problem, where I have labels with 0 for normal and 1 for abnormal. The default distribution of the dataset is highly imbalanced with a ratio of 96:4 ...
4 votes
2 answers
242 views

Benefits of using Deep Learning-specific hyperparameter optimization tools vs. sklearn?

There are quite a few library for hyperparameter optimization that are specific to Keras or other Deep Learning libraries, like Hyperas or Talos. My question is, what's the main benefit of using ...
22 votes
1 answer
3k views

Understanding Timestamps and Batchsize of Keras LSTM considering Hiddenstates and TBPTT

What I'm trying to do What I am trying to do is predicting the next data-point $x_t$ for each point in the timeseries $[x_0, x_1, x_2,...,x_T]$ in the context of a date-stream in real-time, in theory ...
3 votes
2 answers
2k 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 ...
1 vote
2 answers
243 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 ...
1 vote
1 answer
5k views

Converting a Keras model to PyTorch

I have a Keras h5 file that I want to load into the same model but this one is created using PyTorch. Is ONXX a viable intermediary option? What else can I use?
4 votes
1 answer
2k views

Self-attention mechanism did not improve the LSTM classification model

I am doing an 8-class classification using time series data. It appears that the implementation of the self-attention mechanism has no effect on the model so I think my implementations have some ...
0 votes
0 answers
10 views

What is the input to Contrastive Learning models

Contrastive Learning has been used in deep learning for many tasks. The architecture of simCLR is given below. I am using the implementation in the link link. It takes two images as an input not one ...
3 votes
2 answers
223 views

How to train neural word embeddings?

So I am new to Deep Learning and NLP. I have read several blog posts on medium, towardsdatascience and papers where they talk about pre-training the word embeddings in an unsupervised fashion and then ...
0 votes
1 answer
54 views

Reusing a model, pretrained on 19 classes, for just one of those classes

I have a pretrained net for semantic segmentation, which has been trained on the cityscapes dataset and its 19 classes (Person, car, traffic sign, …). One of those is "Person". I am only ...
0 votes
1 answer
225 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
2 answers
312 views

Is there wights of voice or audio for VGG or Inception?

I want to use VGG16 (or VGG19) for voice clustering task. I read some articles which suggest to use ...
0 votes
0 answers
5 views

Reinforcement learning with Q learning doesn't seem to be learning

I'm encountering an issue with my PyTorch-based Q-learning model. Despite implementing the reinforcement learning algorithm, the model seems to be stuck at the same balance level without showing any ...
3 votes
1 answer
135 views

Reinforcement Learning applied to Optimisation Problem

Problem Statement: We are given an optimisation problem; with production centres, source airport, destination airports, transfer points and finally delivered to the customers. This is better explained ...
2 votes
1 answer
29 views

Dicussion for X-vectors

I am posting this question to ask some questions regarding the X-vector embedding proposed by Synder et al. The paper is X-VECTORS: ROBUST DNN EMBEDDINGS FOR SPEAKER RECOGNITION With reference to the ...
2 votes
2 answers
85 views

Is there any text similarity databse available for phrases?

I want to train my application for phrase similarity. I want my model to predict similarity score for phrases as shown in below examples. ex- ...
0 votes
0 answers
152 views

Looking for datasets on automobile parts information for machine learning

I'm embarking on a machine learning project that requires a comprehensive dataset of automobile parts information. The goal is to train a model that can identify and categorize various auto parts, ...
2 votes
1 answer
362 views

Comparison between approaches for timeseries anomaly detection

After various days of research, I could take a global picture of the existing methods to perform anomaly detection on time series, namely: Forecasting with Deep Learning. Eg. RADM or LSTM model ...
0 votes
1 answer
152 views

Difference between class_weight and loss_weights arguments in TensorFlow/Keras

I am creating a neural network using TensorFlow (v2.9.2) for an imbalanced image dataset. While doing so, I noticed that model.compile() method has an argument <...
3 votes
1 answer
54 views

Approach to classify blocks of time series

I am wondering if there exists an approach to classify blocks of time series, and not specifically individual time series. If so, can you point me out papers/articles/tutorials where these type of ...
0 votes
0 answers
11 views

How to build a recommendation system Based on user infos and without ratings?

I would like to build a recommendation system based only on user informations(age,sex,zipcode,and some quiz answers),based on those features i want to recommend assurance products, but i am confused ...
0 votes
1 answer
515 views

LSTM - How to prepare train from a dataset which contains multiple observations for different events

I m using LSTM in a project related to MobiFall dataset which contains falls and daily activitives - such as walking, sitting etc - sensed by accelerometer, gyroscope and orientation sensors in x,y,z ...
3 votes
1 answer
139 views

How to specify version for dependencies so that each one is compatible and stays within a size limit?

I am trying to deploy a web app to Heroku. The free tier is limited to 500 MB. I am using my resnet34 model as a .pkl file. I create model with it using the fastai ...
1 vote
3 answers
3k views

Detect blur image using ssdmobilenet and tensorflowlite

I have clear images of cards vs blurry images of card. My task is to capture photo when the image is not blurry, as you can see from the description I need this code to run in real time on android ...
1 vote
1 answer
43 views

Diffusion Models: Conditioning on Time vs. Noise Level

I am new to SE-Data Science, therefore I hope this is the right place to ask this rather theoretical question. In diffusion models we usually have a time variable which determines the noise schedule (...
0 votes
1 answer
86 views

Data Augmentation Keras length of data

I'm confused when I add data augmentation should I get more data or the same data I tested my x_train length to confirm but I got the same length before augmentation and after augmentation is that ...
1 vote
2 answers
118 views

approach for predicting machine failure using maintenance history

I have been struggling with this problem for a while now and I finally decided to post a question here to get some help. The problem i'm trying to solve is about predictive maintenance. Specifically, ...
0 votes
1 answer
26 views

How to update first layer weights?

I’m trying to make a neural network without using any deep learning library that recognizes numbers in the mnist database. Its structure is: 784 input neurons (for the 784 pixels in the number images),...
0 votes
0 answers
10 views

How does the segmentation in YOLO v8 model work?

I know how YOLO models work for object detection. I wonder what gave the YOLOv8 the ability to apply segmentation at the pixel level. Is there a clever trick? How does it compare to other models like ...

1
2
3 4 5
98