All Questions
10,202
questions
1
vote
0
answers
18
views
Understanding Rademacher Complexity Deeply
empirical Rademacher complexity is defined as,
$$
\hat{R}_{m}(\mathcal{F}, S)=\frac{1}{m} \mathbb{E}_{\boldsymbol{\sigma}}\left[\sup _{f \in \mathcal{F}} \sum_{i=1}^{m} \sigma_{i} f\left(z_{i}\right)\...
- 111
0
votes
0
answers
23
views
Hot to calculate Maximum Normalized log Probability for Active Learning with BERT
I have encountered difficulties understanding the calculation of Maximum Normalized Log Probabilities acording to Shen et al..
With n being the sequence length, yi the label of word i. Xij is the ...
- 1
0
votes
0
answers
37
views
How is it possible to use batches of data from within the same sequence with an LSTM?
ETA: More concise wording: Why do some implementations use batches of data taken from within the same sequence? Does this not make the cell state useless?
Using the example of an LSTM, it has a hidden ...
- 1,246
0
votes
0
answers
10
views
Which structure for this knowledge graph?
I'm currently building a knowledge graph for students based on the textbook. However, I found out that some knowledge are treated as axioms in lower grade but deduction in higher grade. Since I treat ...
0
votes
0
answers
10
views
Python code for Background label removal from Biomedical images
I am doing research in Biomedical Image processing and Deep Learning using Python language. I have labels in the background (as highlighted in yellow ) and Pectoral muscle ( as highlighted in red) of ...
- 1
0
votes
0
answers
26
views
Using rotated bounding boxes - better or not for detection?
I read a few posts here that discussed using rotated bounding boxes, but mostly about how to do it?
I was wondering if anyone has insights on;
In the most used object detection datasets, is it better ...
- 101
0
votes
0
answers
31
views
Multiclass image classification - what approach to use and which models to consider?
I'm working on an image classification project and I need to train a multiclass, multilabel classifier. The dataset is large and some of the images are mislabeled (for a given class, some labels are ...
- 5
0
votes
0
answers
11
views
How to generate multiple captions from an image captioning model in Keras/Tensorflow
I am practicing one of the popular image captioning keras model (LINK IS HERE). Basically this model takes Flickr8k dataset where each image has 5 captions.
...
- 1
0
votes
2
answers
24
views
Can I shuffle data for delivery duration forecast problem?
I'm new to ML and trying to write a solution to a food delivery duration time problem (so called lead time). I used algorithms such as random forest and gradient boosting which gave OK results but not ...
-1
votes
0
answers
15
views
How to calculate Gini or Entropy using sklearn formulas?
How to calculate Gini or Entropy using sklearn formulas?
Can someone calculate it using these formulas for a small dataset with just one feature?
- 1
0
votes
0
answers
22
views
Neural network and logical gates
I have a network witch consist of two fully connected layers (without bias) and a ReLu function in between. The network input is two binary numbers, and the output should be the a logical gate result:
...
- 101
1
vote
0
answers
11
views
how to manage the impact of Covid on building a machine learning model
I need your suggestions for using historical data to build a machine learning model for analyzing the market and build an AI model(tree based model/random forest or regression analysis) for setting ...
- 111
3
votes
1
answer
187
views
What loss function should I use if I only care about the accuracy of one class?
CrossEntropyLoss optimizes the overall classification accuracy as
$$ {n_{\text{correct}} \over N} $$
What loss function should I use if I only care about increasing the true positive rate of one class?...
- 55
-1
votes
1
answer
26
views
Play against your own RL-trained AI from gym retro
so far I have seen people implementing reinforcement learning to build an AI to play and complete games on gym retro, such as street fighter, racing games and so on. However, I was wondering if it is ...
- 1
1
vote
1
answer
17
views
what is `Normalize` for in PyTorch transfer learning tutorial?
in this pytorch tutorial, there is transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]), what is the purpose of this?
(i removed it and the code still ...
- 55
0
votes
0
answers
11
views
why cross entropy loss has to be multiplied by a batch size during an evaluation in transformer model?
I am trying to look through a code of the transformer model from Pytorch. However,
I do not understand why batch size needs to multiply with cross-entropy loss given that loss is calculated based on ...
- 1
0
votes
0
answers
9
views
How to propagate backwards in a neural network with an error term based on the average error over an episode of actions?
I am writing a neural network. I have an average error over an episode of actions to work with in order to update my weights. I know that in a 1 step neural network I take the most recent action of ...
- 3
0
votes
0
answers
29
views
Reinforcement learning SOTA with continuous action space
as of July 2022 what is the SOTA in reinforcement learning with continuous action space?
DDPG PPO … other?
- 101
0
votes
1
answer
46
views
Reconstructing 3D models from 2D images using autoencoders
I went through a research paper ("Voxel-Based 3D Object Reconstruction from Single 2D Image Using Variational Autoencoders") and tried to implement the approach following this diagram:
0
votes
0
answers
19
views
is it possible to train the same neural network with different numbers of inputs and outputs?
is it possible to create an adaptative neural network that can change the number of its inputs and outputs without having to train it each time it changes?
the neural netwrok has to take purchases and ...
0
votes
0
answers
16
views
Markov decision process how to get the correct policy if targets are reached once among N episodes?
I have implemented an MDP on a network such that an agent starts in a node, takes an action from a set of predefined actions and next node (including current). Some of the nodes would result in ...
0
votes
1
answer
35
views
'Advancing' basic models
Good morning.
I am a student running a project using medical data, predicting if the patient will or won't get a disease. The data has about 50k cases and 70 features.
I proposed to train 5 models- ...
0
votes
0
answers
18
views
Is there benefit to autoregressive models for deep RL tasks with long episodes and short required context?
General Case
In deep RL (specifically in the space of policy gradient methods) it seems very common that encoder-decoder models (either transformer or RNN-variant) are used in the policy/value ...
- 101
2
votes
1
answer
154
views
Remove already reached targets from the system to enable reaching other targets?
This may be a very fundamental question, but somehow I can't decide.
I have a graph and the user can take several actions while traversing it and there are multiple points with rewards. When I execute ...
0
votes
0
answers
17
views
Effective fast mobile ocr model
I plan to develop OCR application which is mobile oriented and fast. (like 10~30 fps) The images that will be detected is not wild images. They are refined data such as cell phone capture images. In ...
2
votes
1
answer
287
views
How to deal with small reward values
In my environment rewards are generally small, e.g. [-0.01, 0.01]. My concern is that small reward values might get dominated or distorted by the noise during the training. Does it make sense to scale ...
- 197
1
vote
1
answer
22
views
Rationalle behind SE3 Transformer?
I have just finished reading the SE3 transformer paper (SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks) by Fuchs et-al and although I'm sure I understand less than 50% of the ...
- 121
0
votes
0
answers
13
views
Keras Multiclass Classification - More units than classes on last layer
I am building a CNN to classify spectograms and using the following architecture currently:
...
- 11
1
vote
0
answers
27
views
Help with model architecture for a racing game
I’m working on a model for a racing game using pytorch. The model gets frame from the game as input and produces a controller state as output. The dataset consists of frames from the game and ...
- 11
0
votes
0
answers
17
views
Tracing the source: Which reference did the idea of Transformer's Key-query-value come from?
Since Transformers was proposed in 2017, there have been various interpretation schemes about KQV, but the original text does not seem to explain in detail what this KQV is inspired by. I don't need ...
- 101
0
votes
0
answers
4
views
Can kernel methods be used for prediction on unlabeled data?
In machine learning, kernel methods are often used in supervised learning, especially SVM. I would like to ask can kernel methods be used for prediction on unlabeled data under the premise of ...
- 101
0
votes
0
answers
7
views
How should classification on small images be done?
I want to create an image classifier that classifies very small images (16-32 pixels/side) into around 200 categories. Every category has exactly one image that defines it. The classifier should ...
- 101
0
votes
0
answers
16
views
What is a good neural network approach for this time-based data series
I’m trying to work out a neural network approach to a particular problem and would appreciate any advice.
I have a machine that collects data over a period of time using 2 sensors. Data is collected ...
2
votes
1
answer
74
views
Can an AI have awareness
I guess my question can come under philosophy too. I was thinking about the following:
According to Sir Roger Penrose "No computer has any awareness of what it does.".
Now some context to ...
- 121
0
votes
0
answers
18
views
Different Kernel Initializers in my prediction layer with Transfer Learning could affect performance?
So I have this model right here and the task is to classify 3 labels.:
...
1
vote
0
answers
9
views
Cannot understand/ reproduce reuslt in figure 1 from MobileNetV2?
Hi I am recently reading the MobileNetV2 paper and I found I cannot understand the following figure in the paper.
I made a simple code trying to reproduce the results, but I got opposite results.
...
- 11
1
vote
0
answers
12
views
Is the loss calculation step in Logistic Regression even needed?
I was reading about Logistic Regression and trying to implement the model from scratch. Maybe I am wrong, but I have noticed that the loss calculation step is meaningless in training a Logistic ...
- 33
0
votes
0
answers
12
views
Continuous-valued labels for supervised VAEs?
Referring to these two papers out of several similar ones:
Ilse, Maximilian, et al. "Diva: Domain invariant variational autoencoders." Medical Imaging with Deep Learning. PMLR, 2020.
http://...
1
vote
1
answer
46
views
Time taken to solve cartpole environment using DQN
I am trying to solve the cartpole environment (GitHub) using DQN agent. I have been building my own DQN agent by following a tutorial by Jon Krohn.
I am able to solve the environment with a maximum ...
0
votes
0
answers
13
views
Simplest approach to sentence inversion
I'm looking for an open source library/framework to perform (what I think is called?) sentence inversion. What I'm looking to do is take a sentence like:
...
- 101
0
votes
0
answers
12
views
Why episode mean rewards drawdown?
I'm new to RL. I'm using RecurrentPPO with parameter MlpLstmPolicy and the other defaults.
Why the ...
- 123
0
votes
1
answer
24
views
Metrics using batches v/s metrics using full dataset
I am using training an image classification model using the pre-trained mobile network. During training, I am seeing very high values (more than 70%) for Accuracy, Precision, Recall, and F1-score on ...
- 151
1
vote
1
answer
29
views
LSTM exploding? - multiple parallel time series with multiple variables
I have the following situation:
Stock
Time_Stamps
Feature_1
Feature_2
Feature_n
Price
Stock_1
2019
0.5
1.0
1.0
100
Stock_1
2020
0.7
1.3
0.9
90
Stock_2
2019
0.3
0.9
1.1
110
Stock_2
2020
0.2
0.8
1....
- 11
0
votes
1
answer
25
views
Emergent behavior in AI models that looks similar to natural neural systems
"ImageNet Classification with Deep Convolutional Neural Networks" by Krizhevsky & Sutskever & Hinton describes very interesting emergent behavior of the AlexNet.
It was trained on 2 ...
- 103
1
vote
1
answer
83
views
What type of neural network has an unorganized structure?
I am looking for a network that has an unorganized structure like this, is feed-forward, does not have back-propagation functionality, and is trained with a genetic algorithm.
What would I be looking ...
- 17
0
votes
1
answer
45
views
How special tokens in BERT-Transformers work?
"[SEP] tokens are useful to differentiate the questions from answers through type_ids" Yes, but how is this helping model to understand that "I should look paragraph and generate ...
- 1
1
vote
1
answer
58
views
Can we combine Alpha-zero with GTP-4 to create a general AI?
Alpha Zero is good at looking into the future to plan it's next move.
GTP-4 is good at generating language from previous text.
It seems like combining these two systems would create a general ...
- 2,074
0
votes
0
answers
12
views
Tangent/slope at a point of a recurrent neural network
I am using a recurrent neural network for data of the form $\{(x_t, y_t)\}_{t=1}^T$.
I defined the input of the RNN as a sequence $(x_{t-1}, x_t, y_{t-1})$ and output as $y_t$. My RNN has therefore ...
2
votes
0
answers
30
views
which method are able to approximate the following sequence 1 0 1 0 0 1 0 0 0 1 0 0 0 0 1 5x0 1 6x0
I'm learning deep learning and machine learning techniques, but it looks like neural networks are not capable of predicting the next element in the sequence ...
7
votes
2
answers
984
views
Deep Learning with Best-so-far instead of Where-you-are
It is my understanding that when training a Deep NN in Tensorflow/PyTorch/... we only keep the current state of the network in memory, except perhaps when we manually decide to save the current ...
- 172