All Questions

Filter by
Sorted by
Tagged with
9
votes
2answers
966 views

How does one prove comprehension in machines?

Say we have a machine and we give it a task to do (vision task, language task, game, etc.), how can one prove that a machine actually know's what's going on/happening in that specific task? To narrow ...
1
vote
0answers
7 views

How Training of the “Attention model” in “ Attention is all you need” paper done? What are Keys, Values?

I have recently encountered the paper on NLP. It is very new to me and I am still unable to see how that works. I have used all the resources over there from the original paper to Youtube videos and ...
0
votes
0answers
7 views

What is Annotation in Machine Learning and Types of Data Annotation in ML?

Annotation means, in machine language simply making the things visible, recognizable or understandable in image annotation, pictures, documents and videos by highlighting or marking or adding ...
1
vote
1answer
14 views

Is there any difference between averaged reward and averaged return in reinforcement learning?

reading the Sutton book on Reinforcement learning, I understood reward and return as the same thing. However, in Section 5.6 of the book, 3rd line, first para, it is written: ...
2
votes
1answer
86 views

How can neural networks approximate any continuous function but have $\mathcal{VC}$ dimension only proportional to their number of parameters?

Neural networks typically have $\mathcal{VC}$ dimension that is proportional to their number of parameters and inputs. For example, see the papers Vapnik-Chervonenkis dimension of recurrent neural ...
0
votes
0answers
17 views

why going for “average rewards” than “discounting rewards” in continuous function approximation control problem (Reinforcement learning)

I am studying reinforcement learning for a month by following David silvers's lectures in you-tube and "Sutton and Brato's Introduction to reinforcement learning book"(latest edition) and I came ...
10
votes
5answers
3k views

How do I keep track of already visited states in breadth-first search?

I was trying to implement the breadth-first search (BFS) algorithm for the sliding blocks puzzle (number type). Now, the main thing I noticed is that, if you have a $4 \times 4$ board, the number of ...
1
vote
0answers
20 views

Can we solve an $8 \times 8$ sliding puzzle using hill climbing?

Can we solve an $8 \times 8$ sliding puzzle using a random-restart hill climbing technique (steepest-ascent)? If yes, how much computing power will this need? And what is the maximum $n \times n$ that ...
16
votes
5answers
31k views

Why does C++ seem less widely used than Python in AI?

I just want to know why do machine learning engineers and AI programmers use languages like Python to perform AI tasks and not C++, even though C++ is technically a more powerful language than Python.
0
votes
0answers
6 views

Confusion about the proof that optimizing InfoNCE equals to maximizing mutual information

In the appendix of Representation Learning with Contrastive Predictive Coding, van den Oord et al. prove that optimizing InfoNCE is equivalent to maximize the mutual information between input image $...
0
votes
0answers
11 views

Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks [closed]

I am currently working on Hyperspectral change detection. This study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and recurrent three-dimensional (3D) fully ...
1
vote
1answer
34 views

Should I use minimax or alpha-beta pruning?

Should I use minimax or alpha-beta pruning (or both)? Apparently, alpha-beta pruning prunes some parts of the search tree.
1
vote
2answers
31 views

Are there any good tutorials about training RL agent from raw pixels using PyTorch?

Is there any good tutorials about training reinforcement learning agent from raw pixels using PyTorch? I don't understand the official PyTorch tutorial. I want to train the agent on the atari ...
1
vote
0answers
11 views

What are some good loss functions used to minimize extreme errors in regression and time series forecasting?

I'm working on a time series forecasting task, and, in some specific cases, I don't need perfect accuracy, but the network cannot by any means miss by a lot. So, in detriment of a smaller mean error, ...
0
votes
1answer
23 views

What is correct update when the some indexes are not available?

To update the Q table Q-learning takes the arg max of the Q values - the state, value mappings. For example, in tic tac toe the state XOX OXO -X- contains two ...
1
vote
0answers
9 views

Optimal critic in WGAN

The Kantorovich-Rubinstein duality for the optimal transport problem implies that the Wasserstein distance between two distributions $\mu_1$ and $\mu_2$ can be computed as $$W(\mu_1,\mu_2)=\underset{f\...
3
votes
1answer
64 views
+50

How do I keep my system (online) learning if I can get ground truth labels only for examples flagged positive?

I have a binary classifier (think of it as a content moderation system) that is deployed after having being trained via batch learning. Once deployed, humans review and check for correctness only ...
2
votes
1answer
26 views

True online TD($\lambda$) with dutch trace

In the RL textbook by Sutton & Barto section 7.4, the author talked about the "True online TD($\lambda$)". The figure (7.10 in the book) below shows the algorithm. My question is: at the end of ...
2
votes
1answer
433 views

Is back propagation applied for each data point or for a batch of data points?

I am new to deep learning and trying to understand the concept of back propagation. I have a doubt on when the back propagation is applied. Assume that I have a training data set of 1000 images for ...
1
vote
1answer
36 views

Shouldn't the utility function of two-player zero-sum games be in the range $[-1, 1]$?

In Appendix B of MuZero, they say In two-player zero-sum games the value functions are assumed to be bounded within the $[0, 1]$ interval. I'm confused about the boundary: Shouldn't the value/...
1
vote
1answer
27 views

Convolutional Sequence to Sequence Learning kernel parameters

I am reading the paper Convolutional Sequence to Sequence Learning by Facebook AI researchers and having trouble to understand how the dimensions of convolutional filters work here. Please take a look ...
0
votes
0answers
13 views

How can I build a model that replaces a feature of one image with another feature?

I would like to build a neural network (using TensorFlow) that is able to take two animals, and replace a feature in the second with one in the first. For example, if given a dog and cat, the cat's ...
0
votes
0answers
13 views

How to detect forgery on scanned document images?

I am trying to detect forgeries done after a document is scanned by a scanner. I already tried to access the metadata, and, if it is edited with any software after scanning, then it is easily ...
0
votes
1answer
310 views

Monte-Carlo, every-visit gridworld, exploring starts, python code gets stuck in foreverloop in episode generation

I've been trying to implement policy improvement for Q(s,a) function as per Sutton&Barto reinforcement learning book. The original algorithm with first-visit MonteCarlo is pictured below. I ...
3
votes
1answer
35 views

What happens if the opponent doesn't play optimally in minimax?

I just read an article about the minimax algorithm. When you design the algorithm, you assume that your opponent is a perfect player, i.e. it plays optimally. Let's consider the game of chess. What ...
8
votes
1answer
147 views

Are Q-learning and SARSA the same when action selection is greedy?

I'm currently studying reinforcement learning and I'm having difficulties with question 6.12 in Sutton and Barto's book. Suppose action selection is greedy. Is Q-learning then exactly the same ...
1
vote
0answers
9 views

Sampling from deep belief networks

DBNs are generative models, and usually you sample by thermalising the deepest layer (as it's a restricted Boltzmann Machine), and then forward propagating a sample towards the visible layer to get a ...
2
votes
0answers
21 views

Is better to spend parameters on weights or bias?

If a neural network has a limited number of neuron parameters to find, -let's say only 1000 parameters-, it is generally better to spend the parameters on weights or neuron bias? For example, if each ...
0
votes
0answers
9 views

Train a model using a multi-column text-filled excel sheet

I have an excel sheet filled with my own personal appreciations of movies I've watched, and I want to use it to train an AI model so that it can predict if I'll like a specific movie or not, based on ...
0
votes
0answers
17 views

Conditional Variational Autoencoder - NON Image Data

First I would like to expand an issue I've been dealing with way too long: Creating a conditional Variational Autoencoder with continuous variables in non-image data ( more specifically, time series). ...
2
votes
1answer
53 views

Reinforcement Learning Continuous Control (DDPG): How to avoid thrashing of issued actions? How to reward smooth output over flittering?

Currently I'm working on a continuous state / continuous action controller. It shall control a certain roll angle of an aircraft by issuing the correct aileron commands (between -1...1 continuous). ...
1
vote
2answers
45 views

Continuous control with DDPG: How to eliminate steady state error?

Currently I'm working on a continuous control problem using DDPG as my RL algorithm. All in all, things are working out quite well, but the algorithm does not show any tendencies to eliminate the ...
2
votes
0answers
16 views

Video recognition (specifically video, not individual frames)

There are libraries for recognizing individual video frames, but I need to recognize an object in motion. I can recognize a person in every single frame, but I need to know if the person is running or ...
0
votes
0answers
17 views

Help with deep Q learning for 2048 game getting stuck

I am having trouble making a reinforcement algorithm than can win the 2048 game. I have tried with deep Q (which I think is the simplest algorithm that should be able to learn a winning strategy). ...
3
votes
1answer
1k views

What is the typical AI approach for solving blackjack?

I'm currently developing a blackjack program. Now, I want to create an AI that essentially uses the mathematics of blackjack to make decisions. So, what is the typical AI approach for solving ...
2
votes
2answers
175 views

What are examples of simple problems and applications that can be solved with AI techniques?

What are examples of simple problems and applications that can be solved with AI techniques, for a beginner who is trying to make use of his basic programming skills into AI at the beginning level?
7
votes
1answer
2k views

What do prediction/mean and label/mean represent in this TensorFlow code? [closed]

I am pretty much a beginner in Tensorflow and simply follow a tutorial. There is no problem with my code, but I have a question regarding the output ...
1
vote
2answers
350 views

How to teach a model-based reflex agent for doing some task using machine learning methods?

I would like to know how to teach an agent for performing prediction of the severity of disease and also for alerting patients using machine learning methods. I found the model-based reflex agent can ...
1
vote
1answer
190 views

What do the values of the leaves of the decision tree represent?

This is more of a technical question rather than a practical one. I've exported a decision tree made with python/scikit learn and would like to know what the "value" field of each leaf corresponds to....
4
votes
1answer
470 views

How to parse conjunctions in natural language processing?

Is there an accepted way in NLP to parse conjunctions (and/or) in a sentence? By following the example below, how would I parse I drink orange juice if its the weekend or if it's late and I'm ...
3
votes
1answer
388 views

Can I develop a chatbot to carry on a natural conversation with a human using NLP and neural networks?

I would like to develop a chatbot that is able to pass the Turing test, i.e. a chatbot that is able to carry on a natural conversation with a human. Can natural language processing (NLP) be used to ...
2
votes
1answer
1k views

Why do we use a last-in-first-out queue in depth-first search?

Why do we use a last-in-first-out (LIFO) queue in the depth-first search algorithm? In the breadth-first search algorithm, we use a first-in-first-out (FIFO) queue, so I am confused.
2
votes
0answers
49 views

What are the main technologies needed to build an AI for Warcraft 3's mod DotA?

What are the main technologies needed to build an AI for Warcraft 3's mod Defense of the Ancients (DotA)? Maybe I can take inspiration from OpenAI's work.
0
votes
1answer
18 views

What is the difference between exhaustive nearest neighbor search and k-nearest neighbour search?

I have two lists of feature vectors calculated from pre-trained CNN for image retrieval task: Query: FV_Q and Reference FV_R. <...
9
votes
3answers
617 views

Does Monte Carlo tree search qualify as machine learning?

To the best of my understanding, the Monte Carlo tree search (MCTS) algorithm is an alternative to minimax for searching a tree of nodes. It works by choosing a move (generally, the one with the ...
0
votes
0answers
30 views

How can I combine word2vec with tf-idf to have concatenated features?

I want to develop a focused crawler using deep reinforcement learning and a priority queue that will work as the crawler frontier. I reckon using x = (state, action)...
0
votes
0answers
11 views

How to padding input data in tfjs [closed]

how to padding input data in tensorflowjs ? like in python we use keras pad_sequesces ...
3
votes
1answer
24 views

What is meant by the expected BLEU cost when training with BLEU and SIMILE?

Recently I was reading a paper based on a new evaluation metric SIMILE. In a section, validation loss comparison had been made for SIMILE and BLEU. The plot showed the expected BLEU cost when training ...
1
vote
0answers
10 views

How to understand the matrices used in the Attention layer?

Attention-scoring mechanism seems to be a commonly-used component in various seq2seq models, and I was reading about the original "Location-based Attention" in Bahadanau well-known paper at https://...
0
votes
0answers
10 views

Is there any advantage to using a non-diagonal covariance matrix for a policy distribution?

For reinforcement learning implementations with a gym.spaces.Box action space, which is the product of $k$ real closed intervals, it is common (actually more like ...

15 30 50 per page
1
2 3 4 5
133