All Questions
10,202
questions
1
vote
0
answers
17
views
What are Reservoir computers used for today?
Reservoir computers were very popular in the early 2000s. From what I understand, the advantage of reservoir computers is that, as opposed to generic recurrent neural networks, training is only done ...
- 11
1
vote
1
answer
20
views
How to handle out-of-bound values in Production data?
So I have this model but the data may vary. And it is virtually impossible to always have the values in bounds. If I do I`d have to use larger period leading to concept shift which is worse.
The ...
- 13
0
votes
0
answers
5
views
How to partition the belief space of a POMDP using a "granularity" parameters?
as I understand, to a solve a pomdp we transform it into a belief-MDP. The value function for this belief-MDP is proven to be piecewise linear and convex (PWLC) [Smallwood and Sondik, 1973].To apply ...
- 21
1
vote
0
answers
18
views
Training with extremely imbalanced Dataset
I have a object detection problem which has extremely imbalanced dataset. Lets say there is only one class to detect, say apple or not apple. This detection network will be used in a real case ...
- 11
-1
votes
0
answers
10
views
Recent Advancements - Possible or Science Fiction?
Almost 20 years ago now, I'd read an article about the use of silicon computer chips implanted into human beings - for instance, one who'd lost the use of their arm. They successfully created a link ...
0
votes
1
answer
23
views
In a neural network's neuron that has no activation function, to calculate the delta for the neuron during back propagation do you use a derivative?
I have a neural network that is composed of an input layer, two hidden layers and an output layer. The topology is [151, 200, 100, 1] I am using ReLU activation function on the neurons that are in the ...
- 3
0
votes
1
answer
13
views
Is the discriminator of a GAN network embedded in VAE?
From what I understand, a Generative Adversarial Network (GAN) is composed of an encoder (generator), some synthetic data (fake data) and a discriminator that will penalize any distinguishable real ...
- 3
0
votes
1
answer
20
views
"Tweaking" the cost function to penalize rarer cases more severely
I have a very unbalanced data set that I am running a CNN on for regression. Most of the values are 0, while it is possible for the values to range from 0 to 32.
Is it possible to "tweak" ...
- 115
-1
votes
0
answers
19
views
What are the best recommendation algorithm given user data based on clicks? [closed]
I was studying about filtering techniques for recommendation systems, What is best algorithm for recommendation engine based on numbers of clicks by users ? any article regarding this is useful and ...
- 1
1
vote
0
answers
9
views
Bayesian optimization with confidence bound not working
I have a simple MLP for which I want to optimize some hyperparameters. I have fixed the number of hidden layers (for unrelated reasons) to be 3. So the hyperparameters being optimized through Bayesian ...
- 111
0
votes
0
answers
11
views
UCB algorithm exercise
I am trying to understand the UCB algorithm and I'm trying to understand it using an exercise. Here's the Upper Confidence Bound algorithm explanation:
Now I have the following exercise: Suppose we ...
- 113
1
vote
1
answer
33
views
Can RL still learn if part of my actions are only used once, at the beginning of the episode?
I am working in an environment with 3-dimensional action space. The first two actions are only used at the first timestep and never again. The third action is used at every timestep.
Say, the action ...
- 13
2
votes
0
answers
29
views
What is the most important predecessor of the transformer model?
I'm wondering what the origins of the transformer as proposed in Attention Is All You Need are. The paper itself provides some interesting pointers to the literature on self-attention such as:
A ...
- 66
1
vote
1
answer
16
views
How do you evaluate a k-medoids cluster model?
So I'm planning on clustering a bunch of observation data using k-medoids. There are seven attributes for each instance and the data is numerical and discrete. I'm a little uncertain of how to ...
1
vote
0
answers
14
views
How can I get an integer as output for continuous action space PPO reinforcement learning?
I have a huge discrete action space, the learning stability is not good. I'd like to move to continuous action space but the only output for my task can be a positive integer (let's say in the range 0 ...
- 111
0
votes
0
answers
6
views
How can we measure the importance of each training sample?
I wonder if there's way to measure sample importance. Let's say, we are predicting math test score of a student, and the features given are "English", "Science", "Gender",...
- 1
0
votes
0
answers
31
views
Does this kind of attention exist?
As someone who is new to deep learning, I am only familiar with self-attention.
I'm designing a model. Imagine there are n data, which the $i_{th}$ data can be represented as a vector $x_i$. And the ...
- 21
4
votes
1
answer
52
views
Why is multilayer perceptron a nonparametric model?
E. Alpaydin, Introduction to ML, 4-th edition, page 46:
Over time, it has been realized
in the neural network community that most neural network
learning algorithms have their basis in statistics—for ...
- 43
1
vote
0
answers
7
views
Comparing parameters of networks
Maybe this is a silly way to compare networks, but I would like to compare several networks based on the number of parameters (learnable features) needed in each one. This is with regards to signal ...
- 11
0
votes
0
answers
9
views
uniform gap between training and validation metrics
I am training a neural network (Deep and cross network) for a multi-label classification task (~700 labels). I have around 2.5 million samples, splitted 8/1/1 for train/test/validation. I am seeing a ...
- 121
1
vote
0
answers
14
views
What is the next step in top-down brain simulation after spiking neural networks?
This paper from Yamazaki et al. describes a 68 billion spiking neural network model of the cerebellum. The simulation was about 600 times slower than real time, and the cerebellum is perhaps one of ...
- 41
0
votes
1
answer
22
views
Do we feature scale one hot encoded variables in neural networks? [closed]
If I have a categorical variable in my neural network which I encode using one hot encoding, do I need to feature scale it along with other features before training the artifical neural network? or do ...
- 1
0
votes
1
answer
29
views
Numerical problems with gradient descent
I'm trying to implement a simple neural network for classification (multi-class) as an exercise (written in C). During gradient descent, the weights and biases quickly get out of control and the ...
- 203
1
vote
1
answer
17
views
Datasets input at model.fit produce unexpected results of training loss vs validation loss
Im trying to train a neural network (VAE) using tensorflow and Im getting different results based on the type of input in the model.fit.
When I input arrays I get normal difference between the ...
- 11
0
votes
1
answer
14
views
Do I have enough images? Fine-tuning pre-trained models for bvinary image classification
I am developing a binary image classifier, and my dataset size is of 90 images. From a theoretical point of view, are they enough for fine-tuning a pre-traiend classifier? I plan to test the models ...
- 5
1
vote
1
answer
158
views
Why are AI Safety discussions almost always from the perspective of reinforcement learning?
I have been reading some articles on AI safety and they almost always speak of AI Safety from the reinforcement learning (RL) perspective, i.e. where we have some artificially intelligent agent acting ...
- 131
0
votes
0
answers
15
views
How to use ML.NET to generate texts on pretrained models? [closed]
The task is to generate texts based on a trained GPT-J model. It's quite easy on Python, but I want to add prompt-based text generation functionality to my C# app.
There is nothing similar in the ML....
- 101
0
votes
1
answer
27
views
What is the training accuracy of this model?
I’m trying to classifiy ECG signals using LSTM and MATLAB, the above plot shows that the training accuracy of the system is 100% but when I apply this code to calculate and get the accuracy I get only ...
0
votes
1
answer
77
views
What is the need for _agency_ in AI? [closed]
Why seek to develop artificially intelligent agents? Are there certain advantages and/or needs provided by such supposed intelligent agents that are preferred to simply using intelligent tools that ...
- 131
-1
votes
0
answers
13
views
Semantic network representative alerts [closed]
Semantic network representative is used for what if these
A/logic
B/ analysis
C/ coding
D/ all above
1
vote
1
answer
21
views
Markov's Decision Process - calculate value in each iteration
I have the following decision tree:
I calculated the value of the plan using the following paramenters (given):
{𝑆0 → 𝑎1 , 𝑆1 → 𝑎3 , 𝑆2 → 𝑎4 },
Discount factor (𝛾)= 0.2
I used this formula to ...
- 13
-1
votes
1
answer
20
views
When is it better to utilize machine learning over heuristics?
I learned that 87% of machine learning projects fail due to these five pitfalls:
the scope of the project is too big;
the project’s scope increased in size as the project progressed—e.g., scope creep;...
- 747
0
votes
0
answers
17
views
How to learn the value function in a two-player game?
In single-player games, the optimal policy can be derived from the state value function v(s):
$$
\pi(s) = \underset{a}{\text{argmin}} \sum_{s'} p(s'|a,s)(c(a) + v(s'))
$$
where c(a) is the cost of ...
- 113
0
votes
0
answers
10
views
Using Sparse & Discrete data with a VAE
I currently have a model (currently a VQ-VAE) that takes in one hot encoded image data. (The one hot encoding is the channel dimension for each pixel) Each input image also has a solid background of a ...
- 101
0
votes
0
answers
16
views
Whys and Why-nots using Rust for AI
The title says it all. I would like to know more about what attributes and design choices of Rust that make it a good (or bad) language for the entire ecosystem of AI (both research and production)
...
- 46
0
votes
0
answers
16
views
Why would it be easy to evaluate a probability, when it is hard to sample from for importance sampling?
Suppose we want to perform importance sampling where we have trajectories from some behavioral policy $b$, but we want to perform off-policy evaluation. From these prior questions, I understand that ...
- 101
0
votes
1
answer
22
views
Beginner-friendly machine learning books [closed]
I'm looking for beginner-friendly books about machine learning, if the books contain exercises with solutions it would be better. I have searched on the Internet but there are so many things, can you ...
- 11
0
votes
0
answers
11
views
When does it make sense to switch from discrete action space to continuous?
I'm currently working on a custom RL environment for a PPO model that I'd like to have 40-100 discrete actions with integer-level precision (no decimals). Looking through some papers on the topic, it'...
- 1
0
votes
1
answer
19
views
Limitations of LSTMs
I'm training an LSTM model for classification on accelerometer data, and I get better results when I downsample the signal to 25 Hz than when I use a 50 Hz signal.
I use the same time frame of 1.5 ...
- 111
0
votes
0
answers
4
views
Difference in mask in the end-to-end transformer model>
In the book Deep Learning with Python, 2nd edition François Chollet writes (section 11.5.3. listing 11.36, page 361):
...
0
votes
0
answers
22
views
Agent communication in multi agent system
My task is to compare different ways of communication between two(or more) intelligent agents and decide which has the best performance. I've done my research, and it appears that there are two ways ...
- 1
0
votes
1
answer
13
views
U-Net Maxpooling vs Convolution
Hello I'm implementing a CycleGAN and most of the other implementations I've seen on the internet use Convolution with stride 2 instead of a Maxpoolinglayer for downsample.
On to my question, why ...
- 1
1
vote
0
answers
19
views
How can evaluate the success of my algoritm?
A little bit of context. I have a classification algorithm based on mathematical discriminator and I am not applying any machine learning or AI technique, just moving window and several relative ...
- 11
0
votes
0
answers
13
views
How to include input features in Recurrent Neural Networks
I want to predict a time series. I want to use methods like Recurrent Neural Networks (RNN) but I want to also have some other input features. I mean as far as I know RNN predicts the future just ...
- 141
0
votes
0
answers
8
views
Train YOLO on SKU110K data set
I am new to the deep learning domain. I am working on a project that requires me to create bounding boxes around the products on the shelf. Something like this:
I want the program to detect the ...
0
votes
0
answers
34
views
How to improve the performance of Easy OCR
I am working on a project that requires me to identify a product on a grocery shelf. For that, I am trying to use test recognition and localization to spot a product.
I tried Easy OCR and tesseract ...
0
votes
1
answer
11
views
Dealing with incomplete file sets for a CNN for medical imaging regression problem
I'm trying to solve a medical imaging regression problem using a CNN. Each of the samples in my data set consists of one, two, or three of the following file types:
flair.nii.gz
mprage.nii.gz
swi....
- 115
-1
votes
1
answer
33
views
How to build the actor policy of Soft-Actor-Critic after sampling from a Multivariate normal distribution?
I'm trying to solve LunarLanderContinuous-v2 (https://www.gymlibrary.ml/environments/box2d/lunar_lander/) using Soft Actor-Critic algorithm (following the pseudocode above)
To update the actor policy ...
0
votes
1
answer
14
views
What is the difference between representation and embedding?
As I searched about this two terms, I found they are somehow like each other, both try to create a vector from raw data as I understood. But, what is the difference of this two term?
0
votes
0
answers
30
views
ML algorithm to estimate height and breadth of building like structure from 2D image
Following is my image in the question.
What ML algorithm will help me to estimate the height and breadth of building like towers in the image. The blue painted buildings that look like shadow is the ...
- 71