All Questions

Filter by
Sorted by
Tagged with
2
votes
2answers
33 views

Is there a good ratio between the positive and negative rewards in reinforcement learning?

Is there an ideal ratio in reinforcement learning between the positive and negative rewards? Suppose I have the scenario of moving a robot across the river. There are two options, walk across the ...
2
votes
1answer
27 views

How should I penalize the model proportionally to the error?

I am making an MNIST classifier. I am using categorical cross-entropy as my loss function. I want to make it so that if the correct label is 3, then it will penalize the model less heavily if it ...
0
votes
1answer
31 views

What is the purpose of the arrow $\leftarrow$ in this formula?

What is the purpose of the arrow $\leftarrow$ in the formula below? $$V(S_t) \leftarrow V(S_t) + \alpha \left[ G_t - V(S_t) \right]$$ I presume it's not the same as 'equals'.
1
vote
0answers
12 views

Is there an AI that can complete Deezer Spleeter work?

I have used Deezer Spleeter but it produces echoes aside the stems, so I wonder if there is already an AI that remove echoes noises.
0
votes
1answer
21 views

Indexing tensors in custom loss function with Keras

I'm using a custom loss function in Keras. This is the function: ...
-1
votes
0answers
29 views

Whats Wrong With this Code? [closed]

...
1
vote
0answers
11 views

Similarity of Images (CBIR) for two different cameras

Suppose we have a top down picture of an object (let's say it is a shoe) from an overhead camera. Also suppose we have a database of various objects from a closeup camera. If we feed the top-down ...
-1
votes
1answer
49 views

can i use machine or deep learning in windows instead of Ubuntu? [closed]

I'm new to Machine Learning and want to start to learn it .. Does windows environment be good or i must use Ubuntu
0
votes
0answers
14 views

Tensorflow neural network - inherent overfitting in certain X and Y distributions?

Really open ended question here... I'm working on a classifier model that is used to predict whether some amount is > x, ...
-2
votes
1answer
71 views

What does the cos (or sin) function actually do? [closed]

In the context of ML, using the example equation below, what is the cos function actually doing? It would be great if you could tell me the answer to this very simple example and how you came to the ...
1
vote
0answers
32 views

Implementing Actor-Critic with Experience Replay for Continuous Action Spaces

I have been trying to implement the ACER algorithm for continuous action spaces in reinforcement learning. The paper for the algorithm can be found here: Sample Efficient Actor-Critic with Experience ...
1
vote
0answers
14 views

Can I apply experience on naive actor critic directly? Should it work?

Can I apply experience replay on naive actor-critic directly? Should it work? I have tried that but unfortunately it didn't work.
0
votes
0answers
7 views

Finding effect of inputs on output (shapely values)

I've developed a neural network which takes in n inputs returning m outputs. I want to see which inputs contribute most with each output. One idea I had is for all inputs/output combinations, lock ...
2
votes
0answers
22 views

Evaluation a policy learned using Q - learning

I have been reading literature on reinforcement learning in healthcare. I am slightly confused between the policy evaluation for both SARSA and Q-learning. To my knowledge, I believe that SARSA is ...
0
votes
0answers
9 views

What will be the sequence of steps in a human activity recognition model using LSTM?

In the context of these steps detection, tracking, action classification and activity recognition. Which step will be first and further sequence?
1
vote
0answers
19 views

What are some of the best methods in detecting facial movement using state-of-the-art machine learning models?

I am currently working on implementing a lip reading system in Python using machine learning and image processing. Currently, two initial implementations have provided promising results, albeit not ...
0
votes
0answers
12 views

RNN/LSTM with a large amounts of data

I have sequence data that's quite large - 4x65k per sample. I'm interested in doing classification problems. The number of classes is moderate - ~27 or so What is the suggestion for dealing with this ...
2
votes
1answer
49 views

Is there a mathematical theory behind why MLP can classify handwritten digits?

I'm trying to really understand how multi-layer perceptrons work. I want to prove mathematically that MLP's can classify handwritten digits. The only thing I really have is that each perceptron can ...
0
votes
0answers
17 views

Keras fit generator - ValueError: Failed to find data adapter that can handle input [closed]

I'm trying to fit my deep learning model with a custom generator. When i fit the model, it shows me this error: I tried to find similar questions, but all the answers were about converting lists to ...
1
vote
1answer
16 views

Where can I find good tutorials on user tailored recommendation system for web?

I'm currently working on my uni project, but I have no idea where to start for the user tailored recommendation system on web. Where can I find a good guide on it, preferrably on languages like php ...
0
votes
0answers
10 views

Exhaustive Nearest Neighbor Search vs KNN

I have two lists of feature vectors calculated from pre-trained CNN for image retrieval task: Query: FV_Q and Reference FV_R. <...
1
vote
0answers
18 views

Python code for Mapping Generated Trigram back to individual rows of Comments

I have this query regarding NLP Dataset. Please refer it below: Once we generate trigrams from 5000 rows of reviews, say from entire corpus of text, we generated 1000 trigrams, then if we need to map ...
2
votes
1answer
48 views

Taxi-v3 help. What is meant exactly by convergence of the algo, the highest reward and optimal action for every state?

I started learning about Q table from this blog post Introduction to reinforcement learning and OpenAI Gym, by Justin Francis, which has a line as below - After so many episodes, the algorithm will ...
2
votes
1answer
53 views

Why does KL divergence not satisfy the triangle inequality?

$D_{KL}=\sum_i p(x_i)log(p(x_i)/q(x_i)$ Also can't you make it satisfy the triangle inequality by taking the absolute value of the information at every point?
1
vote
1answer
25 views

I need to select the image from a predefined dataset that are the closest to the input, is this possible or do I even need to use ML/AI?

So as the title states, I have a set of images and I want to process input images and need to select the image that "looks" the most like the input image. I know I've seen something similar where the ...
3
votes
1answer
95 views

Why is the state-action value function used more than the state value function?

In reinforcement learning, the state-action value function seems to be used more than the state value function. Why is it so?
2
votes
1answer
30 views

In a neural network, can colors be used for neurons in place of floating points and would there be any benefit in doing so?

Firstly, some context. I have been reading and watching videos on the subject for around 3 years, but I am still very much a beginner in machine learning and artificial intelligence. That said, I ...
0
votes
0answers
9 views

Details on body measurements prediction

if someone want to do mobile app for body measurements prediction, please what are the necessary things to start with. I need details explanation on this.
2
votes
0answers
36 views

Machine learning frameworks for esoteric languages

Is there a machine learning framework/library for any of the esoteric languages, such as the ones listed here ?
1
vote
0answers
19 views

Is it possible to convert Neural Network code in Python into Matlab code? [closed]

I want to convert the code written in Python into Matlab code. May I know is it possible to do that. Share the available ways or methods to do the conversion. May I know is there any Online ...
0
votes
0answers
21 views

Autoencoder symmetry

I'm building Autoencoder. In the encoding part I use several strided and diluted convolutions per stage of encoding but I'm wondering if I have to construct the decoding part in a symmetric way. My ...
0
votes
0answers
18 views

What is the use of concatenate layer in CNN?

I am not asking what does concatenate layer does in general in point of mathematical operation. But at feature level, what significance does it provide. Does it helps removing false negatives or does ...
0
votes
0answers
9 views

How to encode board before input into the neural net?

Currently I'm working on an educational project (implementation of AlphaZero approach to different types of board games). My biggest concern at the moment is how to encode board before input into the ...
3
votes
1answer
34 views

How to solve the problem of variable-sized AST as input for a (convolutional) neural network model?

In my work I have a given source code for a module. From this module I generate an AST, whose size is dependent on the size of the module (e.g. more source code -> bigger AST). I want to train a ...
1
vote
1answer
34 views

What is teacher forcing?

In the paper Neural Programmer-Interpreters, the authors use the teacher forcing technique, but what exactly is it?
0
votes
0answers
11 views

Keras MLP returns always loss 0.0

I'm implementing a multilayer perceptron with Keras to predict the correct words order in a sentence. I'm using train_on_batch()because I convert each sentence in a ...
1
vote
0answers
30 views

What kind of enemy to train a good RL-agents

So I want to create an RL-agent for two players-board game. I want to use a simple DQN for the first player (my RL-agent). Then, what kind of algorithm that should I use on the second player (my RL-...
0
votes
0answers
11 views

Train a Neuronal Network with MCTS Data

I failed using PPO to train a multiplayer card game. Thus I tested monte carlo tree search (mcts) to predict good moves. This works now (you can test the game here. As calculating a good move using ...
2
votes
0answers
17 views

How do I make my LSTM model more sensitive to changes in the sequence?

I have a many to one LSTM model for multiclass classification. For reference, this is the architecture of the model ...
0
votes
0answers
13 views

What models will you suggest to use in Industrial Anomaly Detection and Predictive analysis on live streamed data?

I have been working on industrial data, that is fed live, I want to explore a few models which might suit for this the best. The data are KPI data from the manufacturing Industry.
2
votes
0answers
28 views

Policy $\pi$ obtained from inverse reinforcement learning vs reward shaping

I am working on a research project about the different reward functions being used in RL domain. I have read up on Inverse Reinforcement Learning (IRL) and Reward Shaping (RS). I would like to clarify ...
-1
votes
0answers
39 views

Will AI still fit in a box without never can go out..?

Following Brian Cantwell Smith : We need some "decidable interpretation" of the world before we can decide over it using logical operations. so "computation" requires a proper "interpretation" of ...
1
vote
1answer
16 views

LSTM model on different time scales

I am a newbie to machine learning. I have an LSTM model that predicts the next output n+1 time 1, params 1, output 1 time 2, params 2, output 2 time 3, params 3, output 3 . . time n, params n, , ...
1
vote
0answers
6 views

Pretrained Models for Keyword-Based Text Generation

I'm looking for an implementation that allows me to generate text based on a pre-trained model (e.g. GPT-2). An example would be gpt-2-keyword-generation (click here for demo). As the author notes, ...
0
votes
0answers
23 views

Why would my neural network run faster on my laptop than on my university's supercomputer?

I am trying to get my neural network running on my university's supercomputer in order to decrease its runtime (not for training, for testing - feedforward runs only). However, the Matlab function I ...
0
votes
0answers
11 views

Which hidden state should I use for a trajectory when incorporating LSTM into RL?

I'm trying to wrap my head around using LSTM in an RL algorithm like actor-critic or PPO. I've found this Github code which presents this in a very simple manner, however I have a very limited ...
0
votes
0answers
7 views

How to perform PGD on a pretrained CNN?

I have a pretrained CNN model using the keras library. I now need to perform a Projected Gradient Descent (PGD) to develop some adversarial examples. To do this, I will need to perform a gradient ...
0
votes
0answers
15 views

Pytorch deep learning models and tabular data representation

I have quite a naive question regarding Pytorch deep learning models and tabular data representation. So, assume I have a dictionary of tables. Each table has some number of columns: categorical and ...
2
votes
0answers
13 views

Tversky Loss paper implementation: Recall/Precision do not improve as stated

I have been trying to implement this paper and I am very much intrigued. I am working on a medical image problem where I have to segment very small specimens on Whole Slide Images (gigapixel ...
1
vote
0answers
13 views

Noise Cancellation on live audio stream

I want to build an application which takes a live audio from source (mic) and filtering the noise (unwanted sounds like chattering, traffic noises) and fetch into an application for further processing....

15 30 50 per page