Questions tagged [ai-design]

For questions related to the design of AI agents, algorithms or models.

Filter by
Sorted by
Tagged with
2
votes
1answer
619 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 ...
3
votes
0answers
175 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 ...
1
vote
0answers
20 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
votes
1answer
35 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 ...
0
votes
0answers
29 views

Superhuman AI to disguise as human players

TL;DR below. You entered a online mini video game. It's a fast-paced hypercasual game. But it's a ranked one - top 10 get prizes. The leaderboard resets and prizes are handed out every couple of ...
2
votes
2answers
615 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 ...
0
votes
2answers
843 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 ...
2
votes
0answers
72 views

An idea I had to create the first Humanoid using Deep Learning

I've come up with an idea on how we could use a combination of Deep Learning and body sensors to create a walking talking living humanoid. Here goes: First, we will recruit 1 billion people and have ...
0
votes
1answer
38 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 ...
2
votes
1answer
87 views

Is my Neural Network program fully connected?

I have the following program for my neural network: ...
4
votes
1answer
526 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 ...
4
votes
1answer
139 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 ...
4
votes
2answers
170 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" ...
1
vote
0answers
26 views

Since there are different types of neurons in adjacent positions in the brain's arrays, should heterogeneous layers be developed?

Below is a taxonomy of neurons. Some of these types occur in different locations in the brain, but there are adjacent neurons of varying types with clearly functional type diversity in many parts of ...
1
vote
1answer
60 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 ...
1
vote
1answer
160 views

Can I filter barking sounds on the television?

My dog goes bonkers every time the sound of a barking dog is heard on a television program. I never noticed this before but literally every movie or show with an outdoors setting eventually includes ...
2
votes
1answer
93 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 ...
7
votes
1answer
218 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 ...
1
vote
2answers
723 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 $h(t)$...
0
votes
1answer
65 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 ...
1
vote
0answers
91 views

Exploration rate decay and training in Q learning

I'm trying to replicate the results of the DeepMind's paper with Breakout included in OpenAI Gym. I wonder how much frames should I keep until I reach the fixed exploration rate. Actually it reaches ...
1
vote
1answer
101 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 ...
0
votes
1answer
888 views

DQN it's not working properly

I'm trying to build a DQN to replicate the DeepMind results. I'm doing with a simple DQN for the moment, but it isn't learning properly: after +5000 episodes, it couldn't get more than 9-10 points. ...
2
votes
1answer
659 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 ...
4
votes
1answer
299 views

Building AI from chess - data shape from simulation [closed]

Problem My problem is the following: Given 1000 wins, losses, and ties from a chess simulation I am using, what shape should each game be (I.e., sequence of moves leading to win/loss/tie) in order to ...
2
votes
1answer
2k 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 ...
6
votes
1answer
191 views

Q-Learning the generic maze solution

After doing some exercices on Q-learning for maze solving, I wondered : my q-learning algorithms solve only ONE maze. The AI doesn't learn how to solve mazes, so how can I achieve it ? For instance ...
3
votes
0answers
62 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 ...
11
votes
1answer
4k views

What are ontologies in AI?

What exactly are ontologies in AI? How should I write them and why are they important?
1
vote
1answer
49 views

What's the difference between poker with public cards and without them?

Example: texas holdem poker vs texas holdem poker with the same rounds, just with no public cards dealt. Would algorithms like CFR approximate Nash-equilibrium more easily? Could AI that does not ...
2
votes
1answer
63 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 ...
1
vote
0answers
22 views

How to handle Feature changes in a model deployed ?

I implemented and deployed with Flask an XGBoost model for a classification problem. But being aware that features importance can change over time to predict probability of label for new data, I ...
11
votes
1answer
2k 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. ...
5
votes
1answer
189 views

What does “hard for AI” look like?

In theoretical computer science, there is a massive categorization of the difficulty of various computational problems in terms of their asymptotic worst-time computational complexity. There doesn't ...
4
votes
1answer
80 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 ...
3
votes
2answers
91 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. ...
9
votes
1answer
2k 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 ...
10
votes
5answers
4k 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 ...
12
votes
2answers
715 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 ...
1
vote
0answers
86 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 ...
4
votes
2answers
209 views

Loss function for singular object detection

What loss function should one use, knowing that input image contains exactly one target object? I am currently using MSE to predict center of ROI coordinates and it's width and height. All values ...
3
votes
1answer
188 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?
2
votes
0answers
46 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 ...
2
votes
1answer
61 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 ...
2
votes
1answer
138 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 ...
3
votes
1answer
93 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, ...
5
votes
3answers
494 views

AI beginners books for coding [closed]

Does anyone know a good book to buy for beginners to coding for artificial intelligence? I have done some coding in Java and a little with Python, but I would be willing to learn a new language too.
4
votes
2answers
235 views

Are Neural Net architectures accidental discoveries?

Recently, I have been learning about new neural networks, which are used for specialised purposes, like speech recognition, image recognition, etc. The more I discover the more I get amazed by the ...
3
votes
3answers
348 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. ...
5
votes
2answers
236 views

What functionality, does control look like in autonomous vehicles levels 4 and 5?

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 ...