Skip to main content

Questions tagged [machine-learning]

For questions related to machine learning (ML), which is a set of methods that can automatically detect patterns in data, and then use the uncovered patterns to predict future data, or to perform other kinds of decision making under uncertainty (such as planning how to collect more data). ML is usually divided into supervised, unsupervised and reinforcement learning. Deep learning is a subfield of ML that uses deep artificial neural networks.

Filter by
Sorted by
Tagged with
3 votes
1 answer
162 views

How do I poison an SVM with manifold regularization?

I'm working on Adversarial Machine Learning, and have read multiple papers on this topic, some of them are mentioned as follows: Poisoning Attacks on SVMs: https://arxiv.org/pdf/1206.6389.pdf ...
0 votes
0 answers
8 views

Adding activation functions in computational graph

In some cases, I saw that the activation function like sigmoid is not added in the computational graph. Is it like a personal choice, or there could be any other reason? In general, is there any hard ...
0 votes
1 answer
44 views

Gradually increasing CPU load on using sentence embeddings model with kmeans

I am having a ML based production application, using flask, deployed on GCP server using gunicorn workers. In each incoming request, a text sentence is received. It is using sentence transformers (All-...
1 vote
1 answer
127 views

Embedding Quality of Transfer Learning model vs Contrastive learning model

I am working on Contrastive learning which is a technique to learn features based on the concept of learning from comparing two or more instances. The downstream task is a classification problem. ...
0 votes
1 answer
143 views

What consequence would a polynomial time algorithm for SAT have on AGI?

$P$ vs $NP$ is a famous problem. We generally believe $P\neq NP$. However suppose there is a polynomial time algorithm of order say $O((n+m)^2)$ or $O((n+m)^3)$ (a low degree polynomial complexity ...
-2 votes
1 answer
50 views

How can I learn about machine learning? [closed]

Is there something out there for beginners? I know programming, but i'm new to AI
0 votes
1 answer
56 views

I want to train a custom chatbot, how should I start

I want to make a chatbot, which can interact like a human(chat gpt). I want to use something completely free like open assistant, etc. I want to learn things along the way, but want to start simple So,...
1 vote
3 answers
935 views

Why the cost/loss starts to increase for some iterations during the training phase?

I am trying to build a recurrent neural network from scratch. It's a very simple model. I am trying to train it to predict two words (dogs and gods). While training, the value of cost function starts ...
0 votes
0 answers
19 views

What AI/ML techniques exist for color palette generation?

Color palette generation for UIs, designers, etc. They are usually created without AI/ML using simple math operations, but what are some examples of AI/ML-based color palette generation?
0 votes
1 answer
74 views

Does Machine Learning focus on discriminative AI while Deep Learning also focus on generative AI?

I know that Deep Learning is subset of Machine learning But is it correct that classical ML algorithms mainly focus on implementing Discriminative AI while DL algorithms implement both Generative AI ...
-1 votes
0 answers
31 views

Find an explicit mapping in the two-dimensional space to transform the linearly nonseparable dataset into a linearly separable one

Q: Find an explicit mapping in the two-dimensional space to transform the linearly nonseparable dataset into a linearly separable one. Show the transformed data points on a plot. I tried many non ...
0 votes
0 answers
16 views

Cross validation and MICE imputation

I'm working on a binary classification problem where I have some missing data. My initial idea was to use MiceForest. I'm also using stratified k fold technique (Data is imbalanced). I also want to ...
2 votes
1 answer
108 views

How exactly does MICE imputation combine multiple datasets into one?

I'm trying to understand Multiple Imputation with Chained Equation (MICE) imputation process (a statistical method for imputing missing data). I have read some articles and I have understood how the ...
0 votes
1 answer
32 views

Can software testers transfer their skills into adversarial testing for AI/LLMS?

My sincere apologies if I am more asking for advice, rather than a solution to a specific problem. However, I am trying to survive in this new world as a software tester. I have been doing test ...
1 vote
1 answer
124 views

Does it classify as Machine Learning?

I have a gaussian distributed time series ($X_t$) with some parameters in my experiment. Suppose I want to know the mean $\mu$. If I define another time series $Y_t$ such that $Y_t=X_t-a$ for all $t$. ...
0 votes
1 answer
34 views

How to build an AI, which is supposed to show emotions to an human User? [closed]

I plan to develop a computer pet that is as natural as possible. I think that neural networks can be used well for this, because they make it possible to constantly adapt to the user and also don't ...
2 votes
1 answer
100 views

Classifying generated samples with Wasserstein-GAN as real or fake

I'm quite new to GANs and I am trying to use a Wasserstein GAN as an augmentation technique. I found this article https://www.sciencedirect.com/science/article/pii/S2095809918301127, and would like to ...
0 votes
1 answer
154 views

Multiclass Ensemble Methods with weak classifiers under 50%

Normally, when using an ensemble method, such as baggin or boosting, in binary classification, there is a reqauirment that each weak classifier have accuracy better than 50%. In the multiclass ...
3 votes
1 answer
382 views

For which problem sizes is Deep Q-Learning suitable and why?

I am wondering for which problem sizes a Deep Q-Learning algorithm is most appropriate. For example, whether it is particularly suited for low complexity problems or not for high complexity problems. ...
1 vote
1 answer
125 views

machine learning for a budgeting application

I am interested in finding references and previous applications where prior year budgets are analyzed to provide guidance for a current year budget. Specifically, each year some two thousand items ...
0 votes
0 answers
19 views

How can I train a decision tree or simple ML model with spike detections

I am looking for some advice for my problem. I have a spike detection algorithm that detections outliers in a signal. I have annotations in my dataset that tells me if I am in 3 events, basal, event A ...
3 votes
3 answers
236 views

Is pre-processing used in deep learning?

I'm new to deep learning. I wanted to know: do we use pre-processing in deep learning? Or it is only used in machine learning. I searched for it and its methods on the internet, but I didn't find a ...
0 votes
1 answer
295 views

How to force Transformer to give more weight to certain tokens

I'm developing an encoder-decoder based transformer model and I would like to ask if there are ways to incentivize or penalize certain tokens during training. I'm working on a translation task where ...
2 votes
1 answer
153 views

Price difference predictions curve almost vanished

With a team, we are studying how it is possible to predict the price movement with high-frequency. Instead of predicting the price directly, we have decided to try predicting price difference as well ...
1 vote
2 answers
699 views

How to extract parameters from a text using AI/NLP

lets say I have three texts: "make a heading that says hello word" "make a heading of hello world" "create heading consist of hello world" How can I fetch those groups ...
2 votes
1 answer
92 views

What would be the steps to create an sentiment analysis chatbot?

We have been assigned a project, in which we have to create a chatbot which will ask question, take the replies, analyse them and give an approximate assessment of the current emotional state of the ...
1 vote
1 answer
185 views

How does the regression layer in the localization network of a spatial transformer work?

I am trying to understand the spatial transformer network mentioned in this paper https://papers.nips.cc/paper/5854-spatial-transformer-networks.pdf. I am clear about the last two stages of the ...
6 votes
1 answer
235 views

How do big companies, like Facebook, model individuals and their interaction?

As a layman in AI, I want to get an idea of how big data players, like Facebook, model individuals (of which they have so many data). There are two scenarios I can imagine: Neural networks build ...
2 votes
1 answer
270 views

Anomaly Detection in distributed system using generated log file

I am developing an AI tool for anomaly detection in a distributed system.  The system supports an interface that combines several individual logs into a single log file generating approx. 7000 entries/...
0 votes
0 answers
13 views

Training agents to avoid collision with nearby agents and obstacles

I would like to create an agent-based simulation model in which a single agent, a person generated at the space's boundary, aims to reach a predefined destination while avoiding nearby agents and ...
0 votes
0 answers
10 views

Understanding matching of a CNN Layer's Output With the Receptive Field of Input Layer

I was trying to implement the following paper: https://arxiv.org/abs/1610.01563 and I came across something that seemed ambiguous to me. On page 4, second paragraph, it says After processing the ...
1 vote
2 answers
1k views

How to create Partially Connected NNs with prespecified connections using Tensorflow?

I'd like to implement a partially connected neural network with ~3 to 4 hidden layers (a sparse deep neural network?) where I can specify which node connects to which node from the previous/next layer....
15 votes
4 answers
6k views

Why did machine learning only become viable after Nvidia's chips were available?

I listened to a talk attended by a panel consisting of two influential Chinese scientists: Wang Gang and Yu Kai, among others. When asked about the biggest bottleneck in the development of artificial ...
0 votes
1 answer
67 views

Extracting keywords from messages

I'm starting a project where I want to extract keywords from given messages. The keywords are for example something like: "hard disk", "watch" or other technical components. I'm ...
0 votes
1 answer
23 views

How do I prepare a multi group time series dataset into a supervised learning one?

ML newbie here, I have a time series dataset that looks like this: ...
1 vote
1 answer
108 views

How to make a model forget specific training it has received?

Does L1/L2 (NAdam weight decay) really make the model "unlearn"? Ok so my question might be dumb but is there any way to "unlearn" a model - and yeah I know there is wieght_decay ...
0 votes
0 answers
41 views

Downsides of training a neural network in constant time

Assumption Let's assume we collect a high quality amount of training data for machine translation for example parallel corpus data from the european parlament combined with other data. We store these ...
1 vote
1 answer
2k views

What is considered the pre-fill, and what is considered the decoding phase in this process?

I've seen conflicting information about this online so I'm looking for clarification. I'm dealing with the causal LLaMAF model specifically. I used to think that a sequence of tokens is generated in, ...
2 votes
3 answers
484 views

Is my flowchart a good representation of the perceptron learning algorithm?

I made a flowchart for a simplified perceptron leaning algorithm. Here is the process of the learning algorithm. Initialize the weights first. Get a training example randomly and make a prediction. ...
1 vote
1 answer
55 views

Why are neural networks optimized instead of just optimizing a high dimensional function?

I know that neural networks are universal approximators when given a sufficient number of neurons, but there are other things that can be universal approximators, such as a Taylor series with a high ...
0 votes
1 answer
43 views

In multi-class classification, how accurate can the model be if there's class imbalance?

My dataset has essentially multi-classification problem, where I have the treatment failure (0), cure (1) and relapses (3) of patients that are associated with a series of covariates (~100 different ...
1 vote
3 answers
265 views

How can I implement 2D CNN filter with channelwise-bound kernel weights?

I would like to bind kernel parameters through channels/feature-maps for each filter. In a conv2d operation, each filter consists of HxWxC parameters I would like to have filters that have HxW ...
0 votes
0 answers
51 views

Neural network with a variable # of neurons

Hello I want to design a AI.The neural network of my AI will consist of 1 input layer of neurons and 1 output layer. What is very unique about the neural network is that the # of input neurons will ...
0 votes
3 answers
586 views

What is loss function in Neural Networks?

I've been studying NNs with tensorflow and decided to code a simple NN from scratch to get a better idea on hwo they work. It my understanding that the cost is used in backpropagation, so basically ...
0 votes
1 answer
77 views

Application of AI for chat-rooms to process data

I have a software that is designed for students to have chat rooms with their classmates, and I want to process the datas being exchanged in the chat-rooms using AI model. The issue is, I don't know ...
0 votes
0 answers
30 views

How to deal with "real" data and closed formed equation in machine learning?

My goal is to perform regression over a set of data coming from the "real world" (sensors). The data is in tabular format. There are 6 independent features with very different values (...
0 votes
2 answers
63 views

Does 1-bit quantization (layers with boolean tensors) machine learning exist?

Does 1-bit quantization machine learning exist? Pytorch's docs on "Quantization" define it as: techniques for performing computations and storing tensors at lower bitwidths than floating ...
0 votes
2 answers
64 views

What do we mean by "AI is correlated"?

From Wikipedia Causal AI is a technique in artificial intelligence that builds a causal model and can thereby make inferences using causality rather than just correlation. One practical use for ...
0 votes
1 answer
34 views

Best way to classify chess pieces on a chessboard (on a square) [more details in the post]?

Ok, so I am working on a project which classifies chess pieces. The input is just a chess piece from a specific chess set on a white / black square on the chessboard. So it's just an image of a chess ...
1 vote
1 answer
86 views

Optimizing a blackbox function with binary states

I have a non-linear black box function, which inputs a vector(size=250) and outputs a scalar value; f(x) = value. The x variable is a vector of size 250 and has ...

1
2 3 4 5
48