All Questions

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

Simple dimension unmatch problem of a simple neural network

In this simple neural network: the derivative for the cost function J when assuming binary cross entropy loss would be If we assume that the dimension of X is 2x1, then wouldn't A1 be 2x1 and A2 be ...
user avatar
  • 1
0 votes
1 answer
15 views

Adding several variables that could be important but can introduce overfitting

Sopose a productivity dataset, where day of the week and months day number are important. I'm thinking to encode these with a one-hot encoding. But if you have few years of data, that features might ...
user avatar
1 vote
1 answer
20 views

fondamental question about regularization techniques to solve overfitting problem in neural networks

I have a text classification neural network based on BERT that overfits. The accuracy on the training dataset is 95%, whereas it is 68% on the validation dataset. Using some classical regularization ...
user avatar
  • 111
0 votes
0 answers
2 views

Systematic analysis of the performance of BERT vs GPT for language generation?

BERT is generally not used for language generation, but it can be. The best comparison of performance between GPT-based and BERT-based generation I'm aware of is from is in the paper BERT has a Mouth ...
user avatar
  • 111
0 votes
1 answer
11 views

How to encode both sentences and categorical data?

I have a DataFrame that contains several columns where some columns contain single words that can be category encoded since I know how many of them are there in total. However one column is an actual ...
user avatar
  • 103
0 votes
0 answers
24 views

Raw Audio Data Learning with CNN: Use zero-centered Input with ReLu?

I am playing around with Conv-Nets on raw audio data. Found some papers that outline different architectures but did not find a lot about the data preprocessing. Can I use a zero-centred input for a ...
user avatar
  • 1
0 votes
0 answers
30 views

Audio classification: Determine the optimum sample length?

I am working on a sound recognition problem with a self-made data set of very long recordings. My current process looks like this: Time series segmentation to extract sound events cropped to a fixed ...
user avatar
  • 1
0 votes
0 answers
7 views

Are there any general guidelines for the architecture of critic network based on actor network?

Suppose the actor-network looks like the following ...
user avatar
  • 3,191
1 vote
0 answers
11 views

How can I learn to transform one input signal (time series) into another?

I'm posting this question here because I've been trying in vain to solve a problem for weeks and I hope some of you might have some useful suggestions. Basically, the problem is as follows. I have 7 ...
user avatar
0 votes
0 answers
3 views

How can I do a time and space complexity comparison of a graph convolutional network vs. a feed forward network / MLP

How can I make a time and space complexity comparison of a graph convolutional network vs a feed-forward network / MLP? Does anybody have an idea how I can compare them?
user avatar
0 votes
0 answers
5 views

How to calculate sample importance, not feature importance

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",...
user avatar
  • 1
1 vote
2 answers
21 views

How to validate my knowledge of models implementation, pros and cons and area of applicability?

So I've been doing ML for ~2 years in industry, I'm a BSc in applied math, finished several courses on ML/DL on coursera, read some specific topics in ML/DL books. Seem to be in the know, more or less....
user avatar
1 vote
0 answers
18 views

Combining Different Inputs in a Neural Network for Numerical Integration

I am building a NN that numerically integrates a non-linear differential equation. Given a DE: $$ \frac{d}{dt}x(t) = f(x, p) $$ with solution $x \in \mathbb{R}^n$ and parameters $p \in \mathbb{R}^m$, ...
user avatar
0 votes
0 answers
23 views

Dall-E Question (probably silly)

I have started to read the Dall-E (1) paper and I have a quick question that will help me a lot. I know the basis of Transformers but only for NLP tasks (Text-to-text). So when i read : "The ...
user avatar
0 votes
0 answers
18 views

Double DQN performs worse than DQN

I have an agent that has to explore a customized environment. The environment is a grid (100 squares horizontally, 100 squares vertically, each square is 10 meters wide). In the environment, there are ...
user avatar
  • 146
1 vote
1 answer
20 views

Why does sklearn perceptron converge for linearly inseparable data points?

I learned that the perceptron algorithm only converges if the dataset is linearly separable. I am implementing this algorithm using scikit learn. The blue and orange points are from the training set, ...
user avatar
0 votes
0 answers
9 views

Extracting behavior (switch On/Off) of an electric load from unlabeled time series data

Following are the details of my dataset: sampling frequency: 1 Hz No. of useful features: 10 The time series dataset is from household wherein I'm required to find ...
user avatar
0 votes
1 answer
18 views

Question regarding matlab computer vision application and color recongnition [closed]

I am thinking of choosing a computer vision project for my school project(detect crack on surface) and the duration I have is roughly 4 months. With no prior knowledge in neural network, is matlab ...
user avatar
  • 103
0 votes
1 answer
41 views

Entirely linear neural network learning non-linear function

I have a neural network that's trained on a sine wave. It uses a lookback of 20 to see what the last 20 predictions were and predict the next value. This network has only a single Linear layer (input ...
user avatar
  • 1,246
0 votes
1 answer
48 views

Which paper describes the effect of learning_starts in Reinforcement Learning?

I have seen many popular RL libraries have a learning_start parameter. This allows the agent to collect enough experiences before training on the replay_buffer. However, I am unable to find the paper ...
user avatar
0 votes
0 answers
17 views

String-Generation for a mapping task

in preparation for a new project i would like to ask for some help finding an approach. The Task: Some kind of material-number in System A (numbers&letters of length X) need to be mapped to ...
user avatar
  • 1
-1 votes
0 answers
27 views

NLP in Automatic Number Plate Recognition [closed]

Is there NLP involved in Automatic Number Plate Recognition? If yes, where is it involved?
user avatar
0 votes
0 answers
11 views

Where have I gone wrong? Data Preprocessing and cross validation

I have the following steps: Fill in missing values - 'mean' for continuous, '10' for discrete columns (discrete columns go up to 0,1,2,3,4,5,6) Feature selection (correlation based, whole dataset) ...
user avatar
0 votes
0 answers
16 views

What happens if I don't do action exploration in DDPG?

Consider the following line from the pseudocode of the DDPG algorithm Select action $a_t = \mu(s_t| \theta_\mu) + \mathcal{N}_t$ according to the current policy and exploration noise If I replace ...
user avatar
  • 3,191
0 votes
1 answer
34 views

Cross Validation and hyperparameter selection correct procedure

I am trying to run a regression supervised learning problem. The dataset is not very large and I wanted to do some cross-validation to avoid overfitting. As I have read it's important to do a ...
user avatar
  • 1
0 votes
0 answers
8 views

Machine Learning Model to assess risk level of individuals of concerns (criminals) and risk level of different public saftey stations

I am working in an academic project where I want to develop ML model to assess different aspects of public safety. I want to narrow down these aspects to 2 items: 1- risk level of individuals of ...
user avatar
0 votes
0 answers
25 views

Why Is There The Term 1/m In Backpropagation

In backpropagation the gradients are used to update the weights using the formula $$w = w - \alpha \frac{dL}{dw}$$ and the loss gradient w.r.t. weights is $$\frac{dL}{dw} = \frac{dL}{dz} \frac{dz}{dw} ...
user avatar
0 votes
1 answer
30 views

How are Neural Networks protected from false training data?

Suppose the training data there exist an element of some data being misleading and some being right, how could the Neural network be trained so that it could filter the right data from the wrong one? ...
user avatar
0 votes
0 answers
18 views

Is it possible to use Reinforcement Learning to learn good weights for another algorithm?

I developed an algorithm that drives a car on a road inside a simulated environment. The algorithm needs weights (parameters) to be set in advance in order to find the best route. These weights are ...
user avatar
0 votes
1 answer
14 views

How to handle anomaly detections with multiple different timeseries' from network traffic?

I would like to implement an anomaly detection algorithm on multiple timeseries' from different network users. Since each user has different behavior and network traffic usage, my question is how can ...
user avatar
  • 131
0 votes
0 answers
15 views

Need help to build career in Computer Vision

I am currently working on generic Machine Learning based projects (Using Pytorch and TF) however I want to work on Computer Vision in the future. In order to make myself ready, I have studied ...
user avatar
  • 1
0 votes
1 answer
16 views

How does a sigmoid neuron act like a perceptron in this scenario?

I have been reading Michael Nielsen’s book online on his website at http://neuralnetworksanddeeplearning.com/chap1.html. I am struggling to understand the second exercise: When c approaches infinity, ...
user avatar
0 votes
0 answers
11 views

Best FAANG Publications on Software Development Aspects of Model Training, Deployment and Monitoring

I recently came upon this good reference from Microsoft on software development aspects of deep learning models and their operationalisation. The paper itself is based mostly on Microsoft's internal ...
user avatar
  • 111
0 votes
0 answers
35 views

What does maximal |Q| mean in DQN?

I am reading this paper and came across the term maximal |Q|. I'd like to know whether it refers to the Q values of the current state $Q(s_t,a_t)$ or that of the target $\mathbb{max}_aQ(S_{t+1}, A_t)$....
user avatar
0 votes
1 answer
18 views

How to detect and deal with data distribution drift/change?

I'm working on a problem in ML to assess the performance of multiple vendors. I have a set of features in my dataset, and it appears each vendor is characterized by its own distribution. This is my ...
user avatar
0 votes
1 answer
17 views

Why do smaller weights converge faster for RNNs?

I am writing a Recurrent Neural Network using only the NumPy library for a binary classification problem. When I initialize the weights with np.random.randn, after 1000 epochs it gets ~60% accuracy, ...
user avatar
  • 15
1 vote
2 answers
27 views

Are RL algorithms suppose to keep learning?

I don't understand if the purposes of RL agents is simply optimizing a model with a reward instead of using labeled data (i.e. in a supervision fashion), or they have also the purpose of keep training ...
user avatar
  • 41
0 votes
0 answers
11 views

How to investigate annual time series data?

I have annual time series data from 2000 to 2020. The brand has introduced new marketing camping in 2010 and I want to investigate the impact of this policy, that's why I am trying to explore the ...
user avatar
0 votes
0 answers
15 views

Why DDPG losses don't decrease while the reward grows?

I've noticed that training a DDPG agent in the Reacher-v2 environment of OpenAI Gym, the losses of both actor and critic first decrease but after a while start increasing but the episode mean reward ...
user avatar
  • 41
1 vote
1 answer
27 views

How to prove that an action-value function optimal for one problem formulation is also optimal for another?

I want to ask about the intuition/where-to-look/what-to-try if I want to prove that an action value function optimal for a problem is also optimal for another reformulation of that smae problem. For ...
user avatar
1 vote
2 answers
38 views

RL solutions for OpenAI Gym environments?

Is there any place where people share their agent's settings for solving OpenAI Gym Environments? For example, I'd like to know what are good parameters for a DDPG agent to learn the task in Reacher-...
user avatar
  • 41
0 votes
0 answers
18 views

Can entropy bonus be used with state-independent log std for stochastic policies?

In this blog article by openai, they say the std of the exploration distribution must be state-dependent, i.e. an output of the policy network, so it works with the entropy bonus, which is an integral ...
user avatar
  • 121
0 votes
1 answer
25 views

Can I use discrete data in the same model as continuous data?

In my dataset, I have some data that is continuous - eg. Age and BMI. I also have some data that is discrete- for example, occupation is labelled as 1 ="Homemaker" 2="Working" 3=&...
user avatar
0 votes
2 answers
20 views

ImageNet Dataset (for PyTorch VGG16 training)

Please can someone describe how to properly obtain the ImageNet dataset (to be precise the ImageNet 2012 Classification Dataset). What I attempted so far The ImageNet webpage refers the user to ...
user avatar
0 votes
1 answer
17 views

classification: the label for the same input is probabilistic

In the usual classification problems, the label for the same input is usually "stable", if I have an image of a dog, then the true label for that exact input is dog every time. but for my ...
user avatar
0 votes
1 answer
50 views

Has there been a study done in tuning hyper-parameters for off-policy reinforcement learning?

I am interested in learning about hyper-parameter tuning for off-policy reinforcement learning (specifically DQN). Could someone point me to papers published or empirical observations in this area?
user avatar
0 votes
0 answers
33 views

Neural Networks in molds industry

I recently began an internship at a moldmaker, where I'm supposed to learn about NN and how to use them (as you can imagine, I don't know much). Each mold is composed of many pieces, and for each ...
user avatar
  • 1
-2 votes
1 answer
56 views

Are there any transcripts of GPT-3 arguing that it is not conscious?

There have been a lot of transcripts showing GPT-3 arguing that it is self-conscious. In response, it was pointed out that GPT-3 can argue anything and pretend to be anything, given appropriate ...
user avatar
  • 107
1 vote
0 answers
24 views

How to decide size of generated dataset in DAGGER agorithm

In the DAGGER algorithm, how does one determine the number of samples required for one iteration of the training loop? Looking at the picture above, I understand initially, during the 1st iteration, ...
user avatar
  • 11
0 votes
0 answers
32 views

How to make neural networks more robust(intuitive explanation)?

Low spectral Norm ensures tight Rademacher complexity and ensures low generalization error for neural nets. Can anyone explain me this in a intuitive manner along with Rademacher view point. ...
user avatar
  • 121

15 30 50 per page