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
0answers
8 views

How does Neural Network denoise an image?

I understand the mathematical formalism behind how neural networks work as a classifier or perform regression analysis. But I face difficulty to realize how they are such a great denoising instrument. ...
0
votes
0answers
20 views

why does my model take 30 mins per epoch when on my GPU? [on hold]

I am training a model with around 200 images and it usually takes around 12 hours or more to complete. My colleagues' work only takes about a hour and a half to train. I am using windows 10 and ...
0
votes
0answers
11 views

How to get same accuracy with identical models in Keras and Tensorflow?

As we all know Keras backend uses Tensorflow and so it should give out same kind of results when we provide same parameters, hyper-parameters, weights and biases initialisation at each layer, but ...
0
votes
0answers
7 views

Problem with convolution neural network gradient checking

I have implemented a deep learning network : Conv -> Relu -> Maxpool -> flattens -> dense -> softmax. the network has 6178 parameters. I am trying to do gradient checking on my deep learning network. ...
0
votes
1answer
12 views

How to get Keras accuracy for each step in an epoch like in Tensorflow?

Like in tensorflow I get accuracy for each step - ...
1
vote
0answers
17 views

Tensorflow and Keras model having same parameters, hyperparameters, weight and bias initialization give different accuracy?

I have made sure that layers,parameters, hyperparameters,kernel_initialization, bias_initialization, seed and dataset are all equal. But still the output for both the models are different. ...
-2
votes
1answer
13 views

Projects for final year students [on hold]

I'm interested in making a final year project based on machine learning.Can you please suggest some topics
1
vote
2answers
23 views

How can I get probabilities of next word with ELMO?

ELMO is a language model, build to to compute the probability of a word, given some prior history of words seen. How can I get this probability from pretained ELMO model?
0
votes
1answer
48 views

What's the proper way to do back propagation in Deep Fully Connected Neural Network for binary classification

I tried to implement a Deep fully connected neural network for binary classification using python and numpy and used Gradient Descent as optimization algorithm. ...
0
votes
0answers
23 views

SRGAN: Adapt the model to the input image?

I wrote and trained my own SRGAN: so I obtained a model that takes 32x32 images as input and gives their improved 128x128 version as output... I sent this template to Google Firebase Machine Learning ...
0
votes
0answers
7 views

Creating a map with camera using Lidar data

I want to create a neural network that learns from lidar data to create a map from image by using camera. I want to start but I need some advices to proceed. I will collect data from lidar and I want ...
0
votes
0answers
11 views

How to get a output of a hidden layer of a single-layer LSTM

How can get the hidden layer outputs in a simple one-layer lstm? ...
0
votes
0answers
14 views

How to prepare data

I have 3 tables Product table: product I'd ( numerical), product ingredients ( words each in one column: ingredient1, ingredient2, etc ), product brand( words), product url, product name Customer ...
1
vote
0answers
6 views

How to Read Photos for Deep Learning on Google Cloud Platform Compute Engine VM Instance, Through Jupyter Lab

I've set up a project on GCP with a Compute Engine VM and Storage Bucket. Access Scopes set to Allow full access to all Cloud APIs Have set a default Region and Zone I believe I have completed SSH ...
-3
votes
0answers
20 views

Java or Python for training and implementing Predictive ANN models in production? [on hold]

What are your opinions? Should I use python since I'm comfortable with it and it is the superior language for machine learning, or should I use Java since it's what my company uses for all our ...
0
votes
1answer
30 views

NMT, What if we do not pass input for decoder?

For transformer-based neural machine translation (NMT), take English-Chinese for example, we pass English for encoder and use decoder input(Chinese) attend to encoder output, then final output. What ...
-3
votes
0answers
12 views

Is Data Mining easier then Theoretical Machine Learning ad Deep Learning [on hold]

Is data mining (text mining for example...) easier than theoretical machine learning and deep learning?
4
votes
0answers
23 views

How to train the predicting boxes in a YOLO network?

I have just finished this tutorial that explains how YOLO networks work. Instead of training the network's weights with a training set, the author loads pre-trained weights and uses them to test the ...
3
votes
0answers
19 views

Detecting abundance of a certain periodic pattern in a time series?

I am really stumped at the moment about how to solve a particular problem. I have many time series like this: This represents the number of hours a person spends on a website each day throughout the ...
-1
votes
1answer
19 views

Deploy local deep learning web app to web

So I've built a (relatively) simple web app with a deep learning image classifier, and I have it running on localhost. How do I upload this to the web so that I can link to it from my website? The ...
0
votes
0answers
20 views

Training on huge data

I'm trying to find a code with n output bits and k input bits. The criterion for the code is that the minimum hamming distance ...
-2
votes
0answers
12 views

time series data modeling for deep learning [closed]

what is the best format to feed the input data, which are time series with varying density over time, to a deep learning network, while at any iteration we want to feed a batch of data including a ...
-1
votes
0answers
10 views

How does Domain Adaptation compare to Data Augmentation?

After a review of the Data Augmentation state of the art and some tests, I am surprised to see that all published papers compare their Domain Adaptation results with vanilla training on the source ...
0
votes
0answers
3 views

Training EfficientNet always throws CUDA exhausted error

I have been trying a hands on the EfficientNet-B6 architecture but evertime I try to train the same, It simply throws up CUDA resource exhausted error. I have been training it on 16GB Tesla P100
0
votes
0answers
4 views

What are different algorithms/methods of selecting triplet's for training a face recognition network?

I want to construct a siamese network using a triplet loss function. For which we need to select training samples( triplets ) for training the network, So how do we select hard triplet's for training ...
0
votes
0answers
16 views

Ensure class balanced batches while hyperparameter tuning keras models with grid search

Ensuring class balanced batches while training keras models is possible using fit_generator method. I used imblearn.keras.BalancedBatchGenerator for that and it works fine! But i wanted to do that ...
0
votes
0answers
8 views

Computer Vision model/solution deployment channels

I am very new to computer vision and am currently dealing with ways to deploy a computer vision model/solution for my current company keeping in mind the following factors :- 1)Capability to demo ...
0
votes
0answers
82 views
+50

Deep Learning for EMC tests

I have a project that is about deep learning of EMC (Electro Magnetic Compability) traits in televisions. Let me explain it in more detail. Every electronic device in the market is obliged to meet ...
0
votes
0answers
7 views

How to use SenseVector Embeddings for deep learning model?

I was facing the issue of false positives due to Word Sense Disambiguation (WSD) for text classification. For eg: 'bank' could be associated to either 'river' bank or 'commericial' bank. Using ...
2
votes
0answers
15 views

Keras model with second to last sigmoid activated Conv1D layer followed by globalMaxPool outputs values outside [0,1]. Why?

I am trying to train a binary classifier. It is a residual network with skip layers etc. but ultimately, the bottom two layers are a 1D convolution with sigmoid activation followed by a global max ...
0
votes
1answer
27 views

why the sigmoid function will be 1 and 0 if we use a fully connected layer that produce a big enough positive(res negative )output

HI I am using a fully connected network that uses sigmoid if we feed a a big enough weights the sigmoid function will finally become 1 or 0 , is there any solution to avoid this ? and will this lead ...
0
votes
1answer
19 views

Traditional Predictive Analytics vs Machine Learning Methods

What is the difference between traditional predictive analytics done using statistics and its tools and, one using machine learning and deep learning? How are we leveraging machine learning and deep ...
0
votes
1answer
31 views

What if there is huge difference between train data and test data?

I trained a model which does well on unseen data,but after deployed on production the data I got is very different,like the highest values in train & test data is ~23,but the data I got from ...
0
votes
1answer
44 views

Autoencoder: using cosine distance as loss function

I'm trying to train an autoencoder (in PyTorch) to reconstruct gene profiles. At the moment I'm using the Mean Squared Error (MSE) loss for training: the model is not overfitting and both the training ...
0
votes
0answers
14 views

How can i draw a circular boundary round the objects rather than Rectangular shape in the YOLO algorithm? [closed]

How can i draw a circular boundary round the objects rather than Rectangular shape in the YOLO algorithm?
0
votes
1answer
31 views

Can I feed only images to simple CNN model without using label data?

I have only image dataset. I want to take only feature map from simple CNN model so can i give only images to model without using label data? How to fit to madel only images?
0
votes
1answer
25 views

Understanding the “Wide” part of Google's wide and deep

Google's wide and deep recommender model sounds really cool, but I'm struggling to believe I'm grasping the wide section right so wanted to check my understanding. Their paper says the following: ...
1
vote
1answer
32 views

Tread wear detection

I have an assignment in which I have to provide a solution to measure the tread depth of a tire using a single rgb image. I thought of two possible solutions: Using CNN to measure the image ...
-1
votes
0answers
22 views

What is the benefit of increasing channels by going deeper in VGG_16?

During my study of VGG_16, I came across the property of increasing channels as we go deeper in the network. Could someone explain how this helps?
-2
votes
0answers
17 views

best pre trained tensorflow model for discriminating different faces?

I have two sets of faces which i'd like a neural network to learn and discriminate. What kind of model or network is best suited for this job? Anyone with experience?
3
votes
2answers
52 views

How to represent audio data in a format that can be used for preprocessing and modelling?

I have a project that I am working on currently. The project is to classify audio data. The data is in two folders train and test...
0
votes
0answers
30 views

Semantic segmentation with MobilenetV3

I've been reading the MobilenetV3 paper[0], there is an example with a segmentation head (Figure 10, below). The paper is somewhat light on details on a few things. I've found a couple of ...
0
votes
0answers
17 views

Deep learning, signal processing and feature engineering

I have a signals represented in python in dense matrices (the values are y-coordinates from a chart - eg. weather temp etc. in different locations around the world). I'm currently trying to process/...
1
vote
0answers
33 views

MultiOutput Regression Model

I have a dataset of 187 data points (numeric data) with 8 features that I need to train to predict 4 target variables. What would be a good algorithm to go about solving this? Ideally, I want an ...
0
votes
0answers
9 views

Regularizing Neural Network for deterministic function approximation

I'm training a neural network to learn a specific pricing function, which is entirely deterministic (i.e. same inputs always produce same outputs). The training occurs with 80 million data points from ...
0
votes
0answers
14 views

Batch Normalization with CUDNN

I want to introduce Batch Normalization in my C++/CUDNN implementation of CNN. The implementation is currently performing well (without BN) on the MNIST dataset. I am using the CUDNN implementation ...
0
votes
0answers
8 views

Training two functions at single network vs separate network

I trained two functions that maps X (n dimension) to Y (1 dimension), which is f(x) and g(x) using ANN. First, I made two networks of input n and output 1, each targeting to fit f(x) and g(x). Second, ...
1
vote
0answers
15 views

Keras high loss and high accuracy in gk bot with reinforcement learning?

I'm making goal-keeper bot in haxball game. It worked well when i trained less but i worked worse when i trained more. Last reinforcement state: 5160 episode - 4171281 steps - 0.05 epsilon: Last fit ...
0
votes
2answers
34 views

What can be the cause of a sudden explosion in the loss when training a CNN (Deeplab)

I am training the following deeplab CNN: https://github.com/tensorflow/models/tree/master/research/deeplab During training I see the following loss: The first 50k steps of the training the loss is ...