Questions tagged [ai-design]
For questions related to the design of AI agents, algorithms, or models. If your question is about designing neural networks, reward functions, or fitness functions, you can use the associated more specific tags "neural-network-design", "reward-design" and "fitness-design", respectively.
267
questions
2
votes
0
answers
125
views
Application of Blockchain in Fraud detection in stock market
I want to develop a fraud detection application in the stock market Using Blockchain technology, we have some pattern that defines the anomaly for use of supervised machine learning but there is one ...
- 121
4
votes
1
answer
256
views
How should I design the LSTM architecture for multivariate time series forecasting problems?
There is plenty of literature describing LSTMs in a lot of detail and how to use them for multi-variate or uni-variate forecasting problems. What I couldn't find though, is any papers or discussions ...
22
votes
1
answer
6k
views
When should I use Reinforcement Learning vs PID Control?
When designing solutions to problems such as the Lunar Lander on OpenAIGym, Reinforcement Learning is a tempting means of giving the agent adequate action control so as to successfully land.
But ...
- 511
3
votes
1
answer
166
views
How do I solve the problem of positioning 11 pieces into a 8x8 puzzle?
I was trying to figure out how to create a solver to the puzzle of putting 11 pieces in a board (8 x 8). I created the game in http://www.xams.com.br/quebra. It is possible to turn the piece 90 ...
- 131
1
vote
0
answers
578
views
Do we need to use the experience replay buffer with the A3C algorithm?
I have skimmed through a bunch of deep learning books, but I have not yet understood whether we must use the experience replay buffer with the A3C algorithm.
The approached I used is the following:
...
- 61
2
votes
1
answer
36
views
Adding input features - is complete re-training required?
I've never worked with very large models that require weeks or months of training, but in such a situation, what happens if you want to add extra features inputs, do you need to re-train the entire ...
- 403
4
votes
3
answers
265
views
Will we be able to build an artificial intelligence that feels empathy?
Nowadays, robots or artificial agents often only perform the specific task they have been programmed to do.
Will we be able to build an artificial intelligence that feels empathy, that understands ...
- 143
4
votes
1
answer
86
views
How should I encode a categorical input?
Let's say you have an input which can take one of 10 different unique values. How would you encode it?
Have input length 10 and one-hot encode it.
Have 1 input but normalise the value between the ...
- 403
2
votes
1
answer
1k
views
How do I choose the number of neurons in the fully-connected layer before the softmax layer?
I am solving a classification problem with CNN. The number of classes is 5.
How can I decide the number of neurons in the FC layer before the softmax layer?
Is it $N * 5$, where $N$ is the number of ...
- 225
3
votes
0
answers
228
views
What can be considered a deep recurrent neural network?
In the paper Deep Recurrent Q-Learning for Partially Observable MDPs, the DRQN is described as DQN with the first post-convolutional fully-connected layer replaced by a recurrent LSTM.
I have DQN ...
- 61
1
vote
0
answers
22
views
Has any research been done to solve word searches with AI?
A simple word search seems too simple to solve with a computer AI. But what I'm interested is how human's solve it. They build up strategies over the course of solving the puzzle. For example:
1) ...
- 2,156
2
votes
1
answer
65
views
How can certain information about the goal be given to the RL learning algorithm?
Policy learning refers to mapping an agent state onto an action to maximize reward. A linear policy, such as the one used in the Augmented Random Search paper, refers to learning a linear mapping ...
- 121
2
votes
2
answers
711
views
Is it a good idea to use BERT to answer a FAQ with semantic similarity?
I have been looking for BERT for many tasks. I would like to compare the performance to answer an FAQ, using BERT semantic similarity and BERT Q/A.
However, I'm not sure it is a good idea to use ...
- 161
0
votes
2
answers
2k
views
How can I solve part b of exercise 3.6 from the book "Artificial Intelligence: A Modern Approach"?
I am trying to solve part b of the exercise 3.6 (page 113) from the book Artificial Intelligence: A Modern Approach.
More specifically, I need to give a complete problem formulation (that is precise ...
- 323
1
vote
1
answer
51
views
How to design an ANN to give an answer that includes two different components?
As an experiment, I want to teach an ANN to play the game of Nim.
The normal game is between two players and played with three heaps of any number of objects. The two players alternate taking any ...
- 1,684
2
votes
1
answer
101
views
Is my Neural Network program fully connected?
I have the following program for my neural network:
...
- 143
3
votes
1
answer
550
views
How to design an AI that discovers more complex concepts on its own?
How would I go about designing a (relatively) simple AI that discovers and invents random more complex concepts on its own?
For example, say I had a robot car. It doesn't know it's a car. It has ...
user21586
3
votes
1
answer
160
views
Is learning possible without random thoughts and actions?
In my view intelligence begins once the thoughts/actions are logical rather than purely randomn based. The learning environments can be random but the logic seems to obey some elusive rules. There is ...
- 143
3
votes
2
answers
184
views
Is "emotion" ever used in AI?
Is "emotion" ever used in AI?
Psychologists have a lot to say about emotion and it's functional utility for survival - but I've never seen any AI research that uses something resembling "emotion" ...
- 211
1
vote
1
answer
73
views
What AI designs are suited for producing title replacements?
Problem: "For a given news article, generate another title for the article if the article is to be published under a different Publication."
Which algorithm will be well suited for this? Should I use ...
- 11
2
votes
1
answer
105
views
How should I predict which characters are going to die in a certain movie?
How would one go about predicting which characters (actors) are going to die e.g. in the next Avengers movie?
To elaborate a bit, given all leaked scripts (fake or not), interviews of different ...
- 166
6
votes
1
answer
248
views
What does it mean to do multi-dimensional processing with tensors in tensor cores?
In some tweets about NeurIPS 2018, this video from NVIDIA appeared. At around 0.37, she says:
If you think about the current computations in our deep learning systems, they are all based on Linear ...
- 161
3
votes
1
answer
1k
views
Why do we need both encoder and decoder in sequence to sequence prediction?
Why do we need both encoder and decoder in sequence to sequence prediction?
We could just have a single RNN that, given input $x$, outputs some value $y(t)$ and hidden state $h(t)$. Next, given $h(t)$...
- 51
0
votes
1
answer
115
views
block of worlds with position aware goal stack planning
Can someone suggest an AI approach to moving blocks, one at a time, assuming control of an robotic arm, to get from the initial state on the left to the final state on right, preferably using goal ...
- 9
0
votes
1
answer
208
views
Can I do oversampling by copying the same image multiple times? Will it effect my neural network accuracy?
I am working on an image data-set. As you may have guessed it is imbalanced data. I have 'Class A, 19,000 images' and 'Class B, 2,876 images'.
So I did an undersampling by removing randomly from the ...
- 101
2
votes
1
answer
1k
views
DQN Breakout adding an extra negative reward to help training?
I'm trying to train a DQN, so I'm using OpenAI gym and Breakout (Breakout-v0).
I have altered the reward supplied by the environment: If the episode is not completed fully, the agent gets a -10 ...
- 173
1
vote
1
answer
3k
views
How to combine input from different types of data sources?
I've to train a neural network using microphone data (wav files), accelerometer sensor data and light sensor data.
Right now the approach I thought was to convert all data into images and combine ...
- 113
4
votes
1
answer
142
views
How to use Machine Learning to create a "Draw-A-Person Test"
The process revolves around a child's drawing. Each part of each drawing corresponds to a score as in the Draw a Person Test conceived by Dr. Florence Goodenough in 1926. The goal of the machine is to ...
- 83
10
votes
1
answer
5k
views
What are ontologies in AI?
What exactly are ontologies in AI? How should I write them and why are they important?
- 243
3
votes
1
answer
82
views
Is there a way that helps me to architect my CNN fundamentally before training?
While we train a CNN model we often experiment with the number of filters, the number of convolutional layers, FC layers, filter size, sometimes stride, activation function, etc. More often than not ...
- 325
15
votes
1
answer
3k
views
Why does the policy network in AlphaZero work?
In AlphaZero, the policy network (or head of the network) maps game states to a distribution of the likelihood of taking each action. This distribution covers all possible actions from that state.
...
- 2,020
19
votes
2
answers
15k
views
How to define states in reinforcement learning?
I am studying reinforcement learning and the variants of it. I am starting to get an understanding of how the algorithms work and how they apply to an MDP.
What I don't understand is the process of ...
- 293
4
votes
1
answer
92
views
Approaches to poker tournament winner prediction?
I’ve done my research and could not find answer anywhere else. My apologies in advance if same problem is answered in different terms on stack-overflow.
I am trying to solve poker tournament winner ...
- 41
3
votes
2
answers
141
views
Are there any discount-factors based on branching factors?
I recently came across this function:
$$\sum_{t = 0}^{\infty} \gamma^t R_t.$$
It's elegant and looks to be useful in the type of deterministic, perfect-information, finite models I'm working with.
...
- 6,177
9
votes
1
answer
3k
views
Is Nassim Taleb right about AI not being able to accurately predict certain types of distributions?
So Taleb has two heuristics to generally describe data distributions. One is Mediocristan, which basically means things that are on a Gaussian distribution such as height and/or weight of people.
The ...
- 161
10
votes
5
answers
7k
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 ...
user9947
10
votes
2
answers
833
views
Do self-driving cars resort to randomness to make decisions?
I recently heard someone make a statement that when you're designing a self-driving car, you're not building a car but really a computerized driver, so you're trying to model a human mind -- at least ...
- 203
1
vote
0
answers
90
views
How can I create a chatbot application where the user can create its own bot?
I am trying to create a chatbot application where the user can create its own bot, like Botengine. After going through google, I saw I need some NLP API to process the user's query. As per wit.ai ...
3
votes
1
answer
195
views
How does one even begin to mathematically model an AI algorithm?
How does one even begin to mathematically model an AI algorithm, like alpha-beta pruning or even its thousands of variations, to determine which variation is best?
- 457
2
votes
0
answers
50
views
What methods are there to detect discrimination in trained models?
I've been researching AI regulation and compliance (see my related question on law.stackexchange), and one of the big take-aways that I had is that the regulations that apply to a human will apply to ...
- 21
2
votes
1
answer
161
views
How should I take into consideration the number of steps in the reward function?
I am currently implementing the paper Active Object Localization with Deep Reinforcement Learning in Python. While reading about the reward scheme I came across the following:
Finally, the proposed ...
- 303
2
votes
1
answer
178
views
How should I encode the input which are 5 cards from a deck of 52 cards?
How should I design my input layer for the following classification problem?
Input: 5 cards (from a deck of 52 cards) in a card game;
Output: some classification using a neural network
How should I ...
- 123
4
votes
1
answer
125
views
What beginner-friendly machine learning method should I use to make teams for my pickup ultimate frisbee club fairly balanced?
A bunch of friends and I play ultimate every week. Recently I wrote a program to choose our teams for us, as well as keep track of certain data (like which players were on which team, which team won, ...
- 43
4
votes
2
answers
290
views
Are Neural Net architectures accidental discoveries?
Recently, I have been learning about new neural networks, which are used for specialized purposes, like speech recognition, image recognition, etc. The more I discover the more I get amazed by the ...
user9947
2
votes
3
answers
367
views
How can we define common sense in an AI agent?
In our lives, we meet different people and describe their common sense based on how they act on a situation. For example, highly extrovert people are able to deal with people without any awkwardness. ...
user9947
2
votes
2
answers
259
views
What functionality, does control look like in autonomous vehicles levels 4 and 5? [closed]
We are doing a research design project on autonomous vehicles and have some questions on AV Levels 4/5; specifically on the roles, impacts and consequences of AV on society, government, users and ...
- 131
2
votes
1
answer
140
views
Relative compute time for each type of layer in a neural network [closed]
Hello,
I would like to know whether this picture from the paper: Distributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability valid?
Questions:
1) Does ...
- 31
2
votes
0
answers
147
views
Can this problem be solved by AI?
I am looking in to building a kind of troubleshooting web application. It would be a form that starts with a first question. Depending on the answer, you get a follow up question and so on until the ...
- 121
2
votes
2
answers
184
views
How to design a recommendation system for shift swapping?
I need to design an algorithm such that it handles the request for shift swapping.
The algorithm will recommend a list of people who are more likely to swap that shift with the person by analyzing ...
- 121
0
votes
1
answer
124
views
How to add contextual follow up like Google Assistant
I am developing PDA like Google assistant on Android. So far, so good.
But now, I want to add contextual follow up like Google assistant so it can keep the train of thought.
As demonstrated here- ...
- 221