Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [deep-learning]

For questions about Deep Learning (also known as deep structured learning or hierarchical learning.)

1
vote
0answers
10 views

Simple weakly supervised Object localizetion using keras. How to visualize the results?

I am following this link : Weakly-supervised-object-localization to create heatmap of the region in an image where the CNN looks to identify the class. As per the above mentioned repository , ...
0
votes
0answers
18 views

Why the loss is nan by using linear activation function in the last layer? [migrated]

I want to use neural network to solve a simple regression problem, and I try to program by myself accroding to lecture Backpropagation and Neural Networks . However, I meet loss divergence problem. ...
1
vote
1answer
25 views

Does changing the order of the convolution layers in a CNN have any impact?

Could changing the order of convolution layers in a CNN improve accuracy or training time?
-1
votes
1answer
23 views

Use Image data from Drive to Colab for Image Augmentation

I am working on CNN. I have saved images in drive to do image augmentation in keras, I have used method (.flow_from_directory(directory)) Since it require directory path. I have mounted drive and give ...
1
vote
0answers
12 views

Is anyone able to reproduce Hinton's matrix capsule networks?

I've been working on Hinton's matrix capsule networks for several months. I searched each corner of the internet. But I couldn't find anyone that can reproduce Hinton's matrix capsule network. Can ...
2
votes
0answers
26 views

DQN Agent not learning anymore - what can I do to fix this?

I am trying to use Deep-Q-Learning to learn an ANN which controls a 7-DOF robotic arm. The robotic arm must avoid an obstacle and reach a target. I have implemented a number of state-of-art ...
1
vote
1answer
22 views

AlphaGo neural network inputs

I have two questions: 1) I have been reading an article on AlphaGo and one sentence confused me a little bit, because I'm not sure what it exactly means. The article says: AlphaGo Zero only uses ...
0
votes
1answer
32 views

Encourage Deep Q to seek short-term reward

I understand that gamma is an important factor in determining the rewards for a deep Q agent, however during testing of my network I am noticing that the agent is outputting more actions to "do ...
2
votes
0answers
11 views

Cluster 2 AWS instances for deep learning model training

I am working on a CNN model for image classification. Currently a single AWS instance (p2xlarge) used for model training. I would like to have one more AWS instance and distribute the load across ...
0
votes
1answer
36 views

How to identify the areas to reduce over fitting?

I am trying classify CIFAR10. The CNN that I generated over fits when the accuracy reaches ~77%. The code and the plot is given below. I tried DropOut, Batch Normalization and L2 Regularization. But ...
3
votes
1answer
52 views

Why is dot product attention faster than additive attention?

In section 3.2.1 of Attention Is All You Need the claim is made that: Dot-product attention is identical to our algorithm, except for the scaling factor of $\frac{1}{\sqrt{d_k}}$. Additive ...
0
votes
0answers
18 views

Turn a NES ROM into object/tile representation

So i have a rom of a hacked super mario game (it has 2 players: Mario and Luigi). Feeding in the raw pixel data of this results in very poor rewards. I was wondering if there was a way to transform ...
2
votes
1answer
48 views

How do I choose the number of neurons in the fully-connected layer before the softmax layer?

I am solving a classification problem with CNN. The number of classes is 5. How can I decide the number of neurons in the FC layer before the softmax layer? Is it $N * 5$, where $N$ is the number of ...
3
votes
1answer
71 views

What is the difference between search and learning?

I came across an article, The Bitter Truth, via the Two Minute Papers YouTube Channel. Rich Sutton says... One thing that should be learned from the bitter lesson is the great power of general ...
1
vote
0answers
19 views

What is the best method to deal with heterogeneous multi agent system MAS?

Heterogeneity: Based on the heterogeneity of agents MAS can be divided into two categories namely: homogeneous and heterogeneous. Homogeneous MAS include agents that all have the same characteristics ...
3
votes
1answer
38 views

How can alpha zero learn if the tree search stops and restarts before finishing a game?

I am trying to understand how alpha zero works, but there is one point that I have problems understanding, even after reading several different explanations. As I understand it (see for example https:/...
1
vote
0answers
33 views

How does bidirectional encoding allow the predicted word to indirectly “see itself”?

Before the release of BERT we used to say that it is not possible to train bidirectional models by simply conditioning each word on its previous and next words, since this would allow the word that’s ...
0
votes
1answer
27 views

When is bias values updated in back propagation?

I am new to deep learning. I have doubts on modifying bias values during back propagation. My doubts are Does the back propagation algorithm modifies the weigh values and bias values in the same pass?...
2
votes
1answer
24 views

Extending a neural network to classify new objects

Suppose a model M classifies apples and oranges. Can M be extended to classify a third class of objects, e.g., pears, such that ...
1
vote
1answer
37 views

Is back propagation applied for each data point or for a batch of data points?

I am new to deep learning and trying to understand the concept of back propagation. I have a doubt on when the back propagation is applied. Assume that I have a training data set of 1000 images for ...
2
votes
2answers
40 views

Is max pooling really bad?

That has been discussion on this. Maybe from Hinton himself. And I heard that many max pooling layers have been replaced by conv layers in recent years, is that true?
0
votes
0answers
11 views

How is the length of an input sequence related to the structure of an RNN?

My question is only with regards to the feedforward part of an RNN. I am following these steps. I am working on prediction of a time series. The time series is a toy model generated by me. It is ...
1
vote
1answer
28 views

IQN bellman target: using Z vs using Q

IQN paper (https://arxiv.org/abs/1806.06923) uses distributional bellman target: $$ \delta^{\tau,\tau'}_t = r_t + \gamma Z_{\tau'}(x_{t+1}, \pi_{\beta}(x_{t+1})) - Z_{\tau}(x_t, a_t) $$ And optimizes: ...
2
votes
0answers
42 views

How to build a neural network that can learn to predict output images?

I am working with a dataset where each input sample is a matrix, and the output corresponding to each input is also a matrix (of shape (400, 10)). The input samples ...
1
vote
1answer
52 views

Does backpropagation update weights one layer at a time?

I am new to Deep Learning. Suppose that we have a neural network with one input layer, one output layer, and one hidden layer. Let's refer to the weights from input to hidden as $W$ and the weights ...
0
votes
0answers
31 views

Double Convolution Layers in Yolov3

Lately, I have been working on yolov3 and have been trying to train it on x-ray images to detect a fracture. However, I have decided that I would want to increase the number of convolution layers for ...
1
vote
1answer
46 views

How to detect LEGO bricks by using a deep learning approach?

In my thesis I dealt with the question how a computer can recognize LEGO bricks. With multiple object detection, I chose a deep learning approach. I also looked at an existing training set of LEGO ...
1
vote
0answers
25 views

What methods are there to generate artificial training examples based on existing training examples?

I have a small dataset (117 training examples) and many features (4005). Each of the training examples is binary labeled (healthy / diseased). Each feature represents the connectivity between two ...
1
vote
0answers
29 views

Combining deep reinforcement learning with alpha-beta pruning

I will explain my question in relation to chess, but it should be relevant for other games as well: In short terms: Is it possible to combine the techniques used by AlphaZero with those used by, say, ...
1
vote
0answers
18 views

how to add the pool4 to the 2 x conv7 in FCN-16s using keras?

Now I'm using tensorflow.keras to implement the FCN-16s, this picture may be different with others, you should focus this it add ...
1
vote
0answers
24 views

What is the internal state of a Simple Neural Attentive Meta-Learner(SNAIL)?

In the paper A Simple Neural Attentive Meta-Learner, the authors mentioned right before Section 3.1: we preserve the internal state of a SNAIL across episode boundaries, which allows it to have ...
3
votes
2answers
61 views

Is reinforcement learning using shallow neural networks still deep reinforcement learning?

Often times I see the term deep reinforcement learning to refer to RL algorithms that use neural networks, regardless of whether or not the networks are deep. For example, PPO (https://arxiv.org/pdf/...
1
vote
0answers
12 views

One dimension deconvolutions or fully connected layers?

I’ve created a variational autoencoder to encode 1-dimensional arrays. The encoding is done through 3 1d-convolutional layers. Then, after the sampling trick, I reconstruct the series using 3 fully ...
0
votes
0answers
16 views

Tensorflow session [migrated]

I am new to deep learning and Tensorflow. I got some basic questions with the sample code below : ...
3
votes
0answers
30 views

How do intermediate layers of a trained neural network look like?

Suppose I have a deep feed-forward neural network with sigmoid activation $\sigma$ already trained on a dataset $S$. Let's consider a training point $x_i \in S$. I want to analyze the entries of a ...
0
votes
1answer
39 views

What does “Wide” vs. “Deep” mean in the context of Neural Networks?

From this article, I read that "to accurately classify data with neural networks, wide layers are sometimes necessary." However, I have seen many implementations and discussions on deep-learning, ...
1
vote
0answers
9 views

Is there a way to compare the similarities among different graphs and then cluster them using Unsupervised learning?

I have a dataset about (240000,23). For my task, I have to use an unsupervised learning method and apply it on every single column separately in order to detect anomalies that might exist. I have pre-...
0
votes
0answers
17 views

Use BERT to answer a FAQ with semantic similarity

I have been looking for BERT for many tasks and I would like to compare performance to answer a FAQ using BERT semantic similarity and BERT Q/A. However, I'm not sure it is a good idea to use ...
4
votes
0answers
29 views

How did the OpenAI 5 for Dota concatenate units?

I am no expert in the field of AI so I apologize if this is a simple/easy question. I was trying to implement a network similar to OpenAI's for another game and I noticed that I did not fully ...
1
vote
0answers
22 views

Why is my generator loss function increasing with iterations?

I'm trying to train a DC-GAN on CIFAR-10 Dataset. I'm using Binary Cross Entropy as my loss function for both discriminator and generator (appended with non-trainable discriminator). If I train using ...
1
vote
0answers
11 views

Hinton's reading list from the removed Coursera MOOC

Geoffrey Hinton's Coursera MOOC was recently discontinued: https://twitter.com/geoffreyhinton/status/1085325734044991489?lang=en The videos however are still available at both on Youtube and on ...
4
votes
1answer
68 views

Unsupervised Learning for anomaly detection

I've started working on anomaly detection in Python. My dataset is a time series one. The data is being collected by some sensors which record and collect data on semiconductor making machines. My ...
2
votes
1answer
18 views

Can Deep Learning be applied to Computational Fluid Dynamics

Can Deep Learning be applied to Computational Fluid Dynamics (CFD) to develop turbulence models that are less computationally expensive compared to traditional CFD modeling?
2
votes
2answers
65 views

Can Reinforcement Learning solve problems, where certain elements in the environement are randomly located?

I want to solve a problem using Reinforcement Learning on a 20x20 board. An agent (a mouse) has to get the highest possible rewards as fast as possible by collecting cheese, which there are 10 in ...
1
vote
0answers
36 views

Running 2 NEAT nets on the same observations

So i have been playing around with neat-python. I made a program, applying neat, to play pinball on the Atari 2600. The code for that can be found in the file ...
1
vote
1answer
40 views

How to chose dense layer size?

I am fine-tuning a VGG16 model on 20 classes with 500k images I was wondering how do you chose the size of the dense layer (the one before the prediction layer which has a size 20). I would prefer not ...
2
votes
0answers
20 views

Hindsight Experience Replay with multiple goals

What if there are multiple goals? For example, let's consider Bit-flipping environment as described in the paper HER with one small change: Now, goal is not some specific configuration, but let's say ...
0
votes
0answers
11 views

Consecutive frames can be discarded when training an SSD/YOLO?

Let's say I have a number of videos, and I want to train an SSD/YOLO (or FRCNN) to detect objects. In the case of a large amount of videos, there will be a lot of frames extracted and transferred to ...
0
votes
0answers
16 views

how to work with multi-labels or two inputs and a output

I’m in this problem and haven’t found a sound solution to it. Been like 20 days now. I have a dataset that looks like this: ...
1
vote
0answers
26 views

Is making lot of 1 versus other model efficient?

I've got classification problem on image, I have 10 classes and when I fine tuned my model on it (I tried VGG, Xception, resnet etc) I have approximatly 83% validation accuracy. I was wondering if ...