All Questions

Filter by
Sorted by
Tagged with
0
votes
0answers
17 views

multi agent deep deterministic policy gradient for discrete actions

I am solving a multi agent problem where each agent has a critic and actor. The problem I am solving has discrete actions and discrete states. I came cross multi-agent deep deterministic policy ...
0
votes
0answers
9 views

Loss & accuracy curves from learning rate range test interpretation

I am working on a project doing experiments with the Learning Rate Range Test (See "A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and ...
0
votes
0answers
20 views

Multiple GRU layers to improve a text generation

I am using the model in this colab https://colab.research.google.com/github/tensorflow/text/blob/master/docs/tutorials/text_generation.ipynb#scrollTo=AM2Uma_-yVIq for Shakespeare like text generation. ...
0
votes
0answers
30 views

Why do some of the algorithms take some extra space around the actual bounding box?

In some of the algorithms, there is a need to crop the object in an image. So, bounding boxes need to be used in order to crop the image to contain object only. Bounding boxes provide the information ...
0
votes
0answers
12 views

Identify Merchants from Transaction Dataset

I have a transaction dataset, each transaction is in an unstructured format. The objective is to identify merchant from each transaction. If we look it from NER point of view, there would be problem ...
0
votes
1answer
72 views

Why is the validation accuracy lower in case of CNN?

I fed the same set of 1.4 million data to two different models: MLP CNN model In both cases, I used the same parameters and hyperparameters. The CNN is showing comparatively lower accuracy (80%) ...
0
votes
1answer
26 views

How to understand the common practices followed for writing a "bounding box" for an image in datasets?

For the image datasets, there may be a bounding box for each image at the dataset. It is an annotation for an image. It is a rectangular box intended for focusing on something inside the image. I read ...
2
votes
1answer
70 views

How to generate a response while considering past questions as well?

User: What is the tallest mountain? Agent: Everest User: Where is it located? # Agent hears: "Where is Everest located?" Agent: Nepal I want to be able ...
0
votes
1answer
29 views

How to show $\rho > 0$ when $\rho$ be minimum attainable from $y_n(W^{*T}X_n)$, where $W^*$ the vector that separates the data?

In the book Learning from Data written (by Abu Mostafa), we have the following exercise: Let $\rho$ be minimum attainable from $y_n(W^{*T}X_n)$ where $W^*$ is the vector that separates the data. Show ...
0
votes
0answers
29 views

Uniform representation of images for machine learning

I'm new to the field of ML so please bear with me while I try to explain what I'm looking for. In most machine learning pipelines that deal with images there is a requirement to "normalize" ...
1
vote
0answers
12 views

What is the reason behind using node embeddings?

I was reading Chapter 3 from the following book (here) on graph representation learning. The chapter is about node embeddings. Question: What is the point of using node embeddings? Do we use them: to ...
1
vote
0answers
11 views

What are examples of node 'features' in graph networks?

Context: I was reading Chapter 3 in the following book (here) about graph representation learning. Before I get to node embeddings, I wanted to make sure that I do understand what is meant by the ...
0
votes
1answer
27 views

How to handle random order of inputs and get same output?

I am a beginner with DL. I did some tutorials and I know the basics of TensorFlow. But I have a problem understanding how to construct more advanced NNs. Let's say I have 6 inputs and a list of 500 ...
1
vote
0answers
29 views
0
votes
0answers
5 views

Do the output of RNN individual layers go through Softmax when going from one layer to the next in a stacked RNN (many to one architecture)?

In most of the online materials that I've read, the equations of RNNs are shown only for a single layer RNN with the output going through softmax (for a many-to-one architecture). I am trying to find ...
3
votes
1answer
56 views

In reinforcement learning, why are policies defined as functions of states and not observations?

I am new to RL and I am following Sutton & Barto's book. My doubt is, when we talk about the policy of our agent, we say it is the probability of taking some action $a$ given the state $s$. ...
1
vote
0answers
22 views

In anchor based object detection, why don't the anchors share the same weights?

After reading about YOLO V3 and Faster R-CNN, I don't understand why the weights for the regression head aren't the same across all boxes of the same size. Given that the backbone of these systems is ...
0
votes
0answers
8 views

Can I perform 3D point cloud per-point labeling from binary classification alone?

All, It seems that the process of individually labeling points in 3D point clouds is no small task. I believe that's why tools like these exist: Sagemaker Pointly But ... what if there are only two ...
4
votes
2answers
48 views

Should I repeat lengthy deep learning experiments to average results ? How to decide how many times to repeat?

I am doing my MSc thesis on deep learning. My model takes many hours to train. Part of what I do is trying different parameters and settings hoping that they will achieve different results. But I ...
0
votes
1answer
43 views

How to find "relationships" between two data representations?

I am a researcher in a field, and new to the whole of AI and machine learning techniques. May the following question is trivial or not framed in the ML language but I try my best. I have two sets of ...
0
votes
0answers
16 views

Boundedness of cell states in MC-LSTM (mass-conserving LSTM)

I'm currently reading Hoedt et al's paper on mass-conserving LSTM. In the corollary it is stated that "[T]he memory cells, $c_k^\tau$, are bounded by the sum of mass inputs $\sum_{t=1}^\tau x^t+...
2
votes
1answer
31 views

Is it possible to apply a particular exploration policy for the on-policy RL agents?

Is it possible to use any particular strategy to explore (e.g. metaheuristics) in on-policy algorithms (e.g. in PPO) or is it only possible to define particular policies to explore in off-policy ...
2
votes
1answer
62 views

What problem does the neural network really solve?

In the image below taken from a Youtube video, the author explains that the neural network can be used to fit a relational graph for a set of data points shown by the green line. And that this is ...
1
vote
0answers
25 views

Is Speech to Speech with changing the voice to a given other voice possible?

Background: I am working on a research project to use (demonstrate) the possibilities of Machine Learning and AI in artistic projects. One thing we are exploring is demonstrating deep fakes on stage. ...
0
votes
0answers
20 views

NLP problem Phrase/Token labeling

Looking for suggestions on how to define the following NLP problem and different ways in which it can be modeled to leverage machine learning. I believe there are multiple ways to model this problem. ...
1
vote
0answers
12 views

Why actual mapping is called as unreferenced mapping in this context of residual framework?

Consider the following statements from the research paper titled Deep Residual Learning for Image Recognition by Kaiming He et al. #1: We explicitly reformulate the layers as learning residual ...
1
vote
1answer
48 views

When should we use CNN instead of MLP?

Is CNN only applicable to time-series data or image data? When should we use CNN instead of MLP?
0
votes
2answers
38 views

Is it possible to apply 2D convolution to 1D data?

Suppose that I have a 1D dataset with 6 features. Can I apply a 2D convolutional neural net to this dataset?
0
votes
0answers
31 views

What deep reinforcement learning algorithm should I use for my problem?

So here is a description of my problem: Essentially, I have a large amount of files filled with code for a number of different tasks. However, lets say these codes are inefficient, and should be ...
2
votes
1answer
23 views

Where can I read about upsampling methods in detail?

In deep learning, we encounter the upsample blocks several times, especially when we deal with images. Consider the following statements from description regarding UPSAMPLE in PyTorch The algorithms ...
0
votes
1answer
25 views

Why using negative integers (as dimensions?) in tensor shapes rather than natural numbers?

Consider the following paragraph from A.1 MULTI-MNIST AND CLEVR of A IMPLEMENTATION DETAILS from the research paper titled ...
0
votes
1answer
29 views

Discard irrelavant states from a MDP

I came across this question about MDP. From the look of it, it seems the full MDP is reducible if the discarded state only have 1 way in and out but is it really so if we change the discounted factor? ...
0
votes
0answers
34 views

How to model the inputs and outputs of the neural network for the Splinterlands card game?

I have recently just completed a course on deep learning and I feel like an intermediate, but I still don't know how to structure this problem. I'm looking to create a NN to play the card game ...
0
votes
0answers
34 views

Which neural network architecture to use to detect very close and very small blobs in high resolution fluorescence images?

Context I am developing a pipeline to automate the detection of small, almost circular, bright blobs (4px) (see first image below) on high-resolution fluorescence images (2048px) and later to assign ...
0
votes
0answers
26 views

Why would the agent always take the same action in the test environment?

I'm trying to set up an agent with PPO2. But I've tried with: A2C DQN PPO2 However, in the test environment, the agent always takes the same action, and the total profit is negative. What can be the ...
0
votes
1answer
32 views

Do authors generally use fully connected layer instead of affine transformation?

We generally encounter the following statement several times The input vector is first fed into a fully connected layer...... Since linear activation functions, such as identity function, can so ...
0
votes
1answer
32 views

Why identity function is generally treated as an activation function?

It is known that the primary purpose of activation functions, used in neural networks, is to introduce the non-linearity. Then how can the linear activation function, especially the identity function, ...
0
votes
0answers
31 views

Using parameter estimation for training a neural network

Assume that we have 4 layers in a neural network. $$z_1 = L_1(x, W_1)$$ $$z_2 = L_2(z_1, W_2)$$ $$z_3 = L_3(z_2, W_3)$$ $$y = L_1(z_3, W_4)$$ Where $x$ is the vector input, $y$ is the vector output ...
0
votes
0answers
11 views

Building Gaussian Mixture VAE using pytorch

I am trying to implement GMM-VAE model using torch. Basically I have a problem implementing for instance equation (1c) where the posterior distribution $p(x|z,w)$ is a Gaussian with the mean and ...
1
vote
0answers
10 views

Continue teaching pre-trained network without forgetting previous data set

I have a rather interesting problem here; I work in the field of image classification for quality assurance. For this I have a dataset of about 1 million images, which I have used to train different ...
1
vote
0answers
57 views

What is the derivative of equation 1 in the paper "Conservative Q-Learning for Offline Reinforcement Learning"?

I am looking at the paper Conservative Q-Learning for Offline Reinforcement Learning, but I'm not sure how they proved theorem 3.1. Here is a screenshot of theorem 3.1. In the proof of theorem 3.1 ...
0
votes
0answers
24 views

What does it mean by "low-level" and "high-level" in features generated by CNN?

Across the literature, the terms "high-level" and "low-level" are generally used as an adjective to the features generated by the convolution neural network. Should I understand ...
0
votes
0answers
24 views

What's the benefit for using a Kalman filter for training a neural network compared to other optimization algorithms?

I found a paper about using an Unscented Kalman Filter(UKF) for traning a neural network. The UKF filter is modified so it works for parameter estimation. Assume that we have a neural network model $\...
1
vote
2answers
34 views

Why do the authors of the T5 paper say that the "architectural changes are orthogonal to the experimental factors"?

Here's a quote from the T5 paper (T5 stands for "Text-to-Text Transfer Transformer") titled Exploring the Limits of Transfer Learning with a Unified Text-...
1
vote
0answers
23 views

Machine learning with raw data alone / or raw data with its statistics

My question is very general and it does not originate from a specific problem. Let's assume that, through experience, we have learned that some statistical property of a set of data is important in ...
0
votes
1answer
31 views

Identify whether two companies are the same

I am trying to solve a problem where I need to map multiple variations of a company name to a single name. For example: say I have a company named ...
1
vote
0answers
44 views

What is the confusion loss for adversarial learning?

What is the confusion loss used in domain adaptation (DA) for adversarial learning/GANs? See this paper. Two domains: $s$: source domain $t$: target domain Generator/Discriminator setting: $M_s:x_s\...
0
votes
0answers
30 views

How to fine-tune a model which was pre-trained on a corpus that contains words with different meanings than the meanings of those words on my corpus?

I have a scenario in which we should leverage previously asked questions (not questions pairs, single question in a column) to locate similar questions within those questions. How can I fine-tune my ...
0
votes
1answer
63 views

How do I prepare this 3D data for NN?

How do I prepare the info of 3D models to use with NN? For example, I have thousands of models with boxes similar to the ones in the image below. I can extract the vertices and their normals that make ...
0
votes
0answers
49 views

What are the different possible usages of the word "i.i.d" in machine learning?

The acronym "iid" stands for "independent and identically distributed". It is a property of a sequence of random variables. You can read here for more details. This question is ...

15 30 50 per page
1
3 4
5
6 7
195