All Questions
727 questions
1
vote
1
answer
24
views
How do neural scaling laws explain the improvements from LSTMs to Transformer based models
I was reading about a study on neural scaling laws from 2017 and they noted this as a summary. From Hestness, Joel; Narang, Sharan; Ardalani, Newsha; Diamos, Gregory; Jun, Heewoo; Kianinejad, Hassan; ...
- 279
0
votes
0
answers
37
views
When should you use a transformer and when LSTM, GRU and other Neural Networks?
There is a lot of information on the Internet that the transformer is better than RNN in everything, but is it true?
Examples:
«What if I need to translate words?»
«Generate text, images?»
«Play a ...
0
votes
2
answers
55
views
Is there any actual difference between these 2 definitions of a state value function?
The definition of the value function in TRPO paper is
\begin{align}
V_\pi(s_t) &= \mathbb{E}_{a_t,s_{t+1},\ldots} \left[ \sum_{l=0}^{\infty} \gamma^l r(s_{t+l}) \right], \\[10pt]
a_t &\sim \pi(...
- 139
1
vote
1
answer
31
views
Is it useful for ML or DL algorithms to create differential variables from cumulative variables in a dataset?
I'm working on a dataset that contains several cumulative variables, which are values that always increase and depend on their previous values (such as an odometer reading in a vehicle). My aim is to ...
- 11
1
vote
1
answer
39
views
Time resolution with dataset
Suppose I have one dataset which every point (means every row) is per 15 minutes, but my requirements is time resolution of an hour.
If I use the dataset which is time resolution of 15 minutes, would ...
- 111
0
votes
1
answer
31
views
A Request for Research on Small-Sample Fine-Tuning of Large Models in Actual Production
I'm currently working on a production task to perform small-shot fine-tuning of large pretrained models in a live production environment. Given that we plan to fine-tune directly from the data ...
- 19
1
vote
3
answers
47
views
Theoretical justification for data augmentation
It is common practice when training deep learning algorithms to augment the training data. For example, in computer vision an image might be flipped, rotated, cropped etc., adding new training samples ...
- 231
0
votes
0
answers
17
views
Well known multidimensional recurrence relations/sequences
I'm using ML to approximate multidimensional recurrence relations, and am wondering where there are any well known or commonly used multidimensional recurrence relations.
E.g. for a 3D array where ...
- 1
0
votes
0
answers
15
views
(distributed) DataLoader when batches are correlated, pitfals?
I know how to implement Datasets and Dataloaders in pytorch.
However, when it comes to distributed and correlated batch generation, I need advise.
Background
I have a network that generates a new ...
- 111
0
votes
1
answer
108
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 ...
- 181
0
votes
1
answer
48
views
0
votes
0
answers
21
views
Deep Learning: Architecture vs. Features for Performance?
In deep learning, when aiming for peak metric performance, is a well-designed architecture with imperfect features/dataset generally preferable to a poorly designed architecture with high-quality ...
1
vote
0
answers
20
views
Best method for finding centroid of 3D object?
I'm somewhat new to machine learning and want to implement a manufacturing application that finds the centroid of an irregular object so that as little material as possible is removed during ...
- 11
0
votes
2
answers
107
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 ...
- 117
0
votes
0
answers
34
views
About copyright problem in creating benchmark dataset for pre-modern books
I'm a newbie so please answer me softly.
Basically I want to create a benchmark dataset in Vietnamese pre-modern books (when the context, content, dialect, grammar, aged printed quality, printing mold ...
- 71
0
votes
1
answer
40
views
Can I scale subsets of my dataset independently to handle different feature ranges?
I am currently making an LSTM model to predict the change in value of a stock for each day. My dataset consists of 4 years of data for 30 different stocks along with some financial metrics such as RSI,...
2
votes
2
answers
556
views
Is it easier to use back-propagation or genetic algorithms to teach an artificial intelligence?
I am making a very simple neural network for a school project, and I would like to know what the best and easiest way to "teach" a neural network would be. From what I know, backpropagation ...
- 23
0
votes
0
answers
26
views
Is it necessary that the number of samples of one class be balanced with other classes in a classification problem?
Consider a classification problem using machine learning techniques (e.g. malware detection). In such a problem, is it necessary that the number of samples from each class (in the mentioned example, ...
- 11
0
votes
1
answer
74
views
How do I know that my dataset is good enough for training a neural network?
Suppose I have a clean (no outliers and normalized) dataset for training a neural network.
The training process is expected to take almost a week. So, before I start training, I want to know if this ...
- 339
0
votes
0
answers
21
views
Are there leaderboards/tables/stats that compare inference times between close-sourced LLMs such as GPT 3.5/4 and Claude?
https://huggingface.co/spaces/optimum/llm-perf-leaderboard is great to compare inference times between LLMs but it misses close-sourced LLMs such as GPT 3.5/4 and Claude.
- 3,267
1
vote
2
answers
1k
views
What is the difference between densenet and resnet?
Is the only difference between the two how the skip connection is combined? Resnet combines skip connections through addition and Densenet through concatenating.
The Densenet paper appears to be ...
- 233
1
vote
1
answer
98
views
Is there any advantage of genetic algorithm (or programming) over Neural Networks? [closed]
I am planning to switch from neural networks to genetic algorithms (GA) and programming (GP).
One of the main hassles of working with neural networks is that it requires a large amount of training ...
- 339
0
votes
0
answers
86
views
What are some tips of curating a dataset to fine-tune a code-completion LLM?
There is a new SDK that I am working on and I want to know what are some ways of automatically curating a dataset to train a code-completing LLM to deploy as a VSCode plugin? Hacky ways are ...
- 111
0
votes
2
answers
61
views
Should I define my problem as image segmentation or detection?
I have a problem and have to decide wether it's an object detection or object segmentation problem. I want to use Yolov8 for training. We already have hundrets of images but they aren't labeled yet. ...
- 113
2
votes
1
answer
109
views
Do different camera angles affect the performance of the deep learning model?
I'm working on a project to build a face recognition system and I have a question: do different camera angles affect the performance of the deep learning model?
For example, in CCTV, training data and ...
- 23
1
vote
1
answer
1k
views
When to use Pruning, Quantization , Distillation and others when optimizing speed
I want to understand how to optimize models for inference speed and am seeking some advice and best practices for the same.
I am a little bit aware of the concepts of pruning, quantization, and ...
- 789
4
votes
2
answers
3k
views
What are the differences between seq2seq and encoder-decoder architectures?
I've read many tutorials online that use both words interchangeably. When I search and find that they are the same, why not just use one word since they have the same definition?
user78615
1
vote
1
answer
133
views
Why are these two implementations of the $\epsilon$-greedy policy different?
According to the book Reinforcement Learning An Introduction, the epsilon greedy policy can generally implemented as:
$$
\pi(a|s) =
\begin{cases}
\frac{\epsilon}{|A|} + 1 - \epsilon & \text{if } ...
- 195
2
votes
1
answer
541
views
What are the similarities between Q-learning and Value Iteration?
This is the explanation of value iteration in our notes where you keep applying bellman optimality equation till it stops changing and then acting greedily wrt the value function gives the optimal ...
- 23
1
vote
3
answers
83
views
Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?
Imagine we have some sort of "next token predictor," either with transformer architecture, LSTM, or just a HMM (though the terminology I use here will be less aligned to HMMs, I believe the ...
- 113
1
vote
1
answer
48
views
Is there validation data in K-fold cross-validation?
We know that in machine learning the dataset is divided into 3 parts: training data, validation data and test data.
On the other hand, K-fold cross-validation is defined as follows:
the dataset is ...
- 1,115
0
votes
1
answer
248
views
What is the difference between Machine Learning model, algorithm and hypothesis?
I'm fairly new to Machine Learning field and still to grasp the basics, so this question may seem very stupid, but what is the difference between Machine Learning model, algorithm and hypothesis?
Like ...
0
votes
1
answer
33
views
What are the differences between loss surfaces that "derive"from different observations?
If I understand right that each observation whithin a dataset, creates a different loss surface where we want to find the global minimum.
How different those surfaces one from another?
Would it be ...
- 303
0
votes
1
answer
141
views
Which search algorithm expands nodes closest to the goal?
I want to know which search algorithm among A* and Best-First Search and Greedy First Search expands nodes closest to the goal. I have three opinions about A* and Best-First Search and Greedy First ...
- 3
0
votes
1
answer
170
views
What is the difference between A/B testing and Reinforcement Learning?
I was learning ML, and I learnt a new section called, Reinforcement Learning. After some research on web, I found that it is a trial and error technique by which ...
1
vote
1
answer
765
views
What role does data quality plays in the LLM scaling laws?
DeepMind released the Training Compute-Optimal Large Language Models paper in 2022 which describe some scaling laws for LLMs. As far as I understand this is the most accredited reference to estimate ...
- 183
0
votes
1
answer
57
views
AI and Machine Learning Prediction Algorithms for predicting outcome results of Hypothetical poll
Can artificial intelligence and Machine Learning Prediction Algorithms assist in deciding the Outome Results of a Hypothetical Online Poll?
Poll: Selecting favorite American President till date.
...
- 139
0
votes
1
answer
192
views
How are the intuitions and mathematics of attention mechanisms related to those of PageRank?
Excuse me if you find this question too vague and not fitting to this forum and feel free to close it. The overall goal of my question is to get a better intuition of the attention concept and ...
4
votes
1
answer
291
views
How does Monte-Carlo Tree Search Compare to MCMC?
Monte-Carlo Tree Search was the method used for AlphaGo my understanding is: it would randomly search the state space of possible moves where the probability of choosing a move was proportional to the ...
- 454
1
vote
1
answer
139
views
Creating a Dataset from Time Series Data
Context
I'd like to build a regression model for this data to predict a user's test scores given their study habits.
Basically, the variables are in two separate csv tables similar to the ones below. ...
- 113
4
votes
1
answer
2k
views
What's the difference between GPT3.5 and InstructGPT?
I read about the different model series in GPT3.5 here - https://platform.openai.com/docs/models/gpt-3-5
At the beginning of the page, it mentions to look at https://platform.openai.com/docs/model-...
- 41
1
vote
1
answer
85
views
Are on-policy algorithms always better than off-policy ones?
I am studying RL and I have a question: Are on-policy algorithms always better than off-policy ones?
0
votes
1
answer
59
views
What are possible reasons for the validation loss increasing with more data?
I trained a neural network on an NLP problem and compared the loss and BLEU score on the validation data with the same training parameters in two scenarios: a) when I trained on 25% of the data, b) ...
1
vote
2
answers
70
views
Is data useless for a neural network if some inputs are derivatives of other inputs?
That is, if some of the inputs to a neural network can be calculated by a pre-determined function whose variables are other inputs, then are those specific inputs useless?
For example, suppose there ...
- 67
1
vote
0
answers
270
views
How to get ZINC 500k dataset?
I have been using the ZINC graph regression dataset available through pytorch geometric datasets for a while now in two of its modes (12k examples and 250k examples). However, in the PapersWithCode ...
- 211
1
vote
1
answer
96
views
How are these two equations for the optimal state-value function equivalent?
By substituting the optimal policy $\pi_{\star}$ into the Bellman equation, we get the Bellman equation for $v_{\pi_{\star}}(s)=v_{\star}(s)$:
$$ v_{\star}(s) = \sum\limits_a \pi_{\star}(a|s) \sum\...
- 1,115
3
votes
1
answer
589
views
Do the terms 'sample complexity' and 'sample efficiency' mean the same thing in RL context
For example, the the paper Soft Actor-Critic:Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor, both terms are mentioned but without explaining. I have seen them in other ...
- 195
0
votes
1
answer
4k
views
What's the difference between classification and segmentation in deep learning?
What's the difference between classification and segmentation in deep learning?
In particular, can the classification loss function be used for segmentation problems?
1
vote
0
answers
38
views
What is the precise relation between Swarm Intelligence and Ensemble Methods?
I come from the machine learning side of AI, and have recently become more interested in the bio-inspired side of AI. Specifically I started reading about swarm intelligence and immediately started ...
- 11
0
votes
0
answers
50
views
Are autoencoders computationally cheaper than MLPs with the same number of neurons?
Are autoencoders computationally cheaper than other neural networks such as MLP with the same number of neurons?
I have read in some papers that autoencoders train the network faster, and I could ...
- 1