Questions tagged [neural-networks]

For questions about a artificial networks, such as MLPs, CNNs, RNNs, LSTM, and GRU networks, their variants or any other AI system components that qualify as a neural networks in that they are, in part, inspired by biological neural networks.

Filter by
Sorted by
Tagged with
4
votes
1answer
245 views

ReLu, Sum and Convolution Layers to Count Pixels of Certain Color

Below is an excerpt in an instructor's manual on ML that is explaining deep neural networks, using cat recognition (what else!) from images as example. On how DL performs this feat, the excerpt said ...
7
votes
3answers
866 views

How do I know if my backpropagation is implemented correctly?

I'm working on implementation of the backpropagation algorithm for a simple neural network which predicts a probability of survival (1 or 0) and I can't get it above 80% no matter how much I try to ...
3
votes
1answer
870 views

Solving Crossword Puzzles

I have to model an AI that should be able to understand clues and find the answer from a specified word database. I came across several papers that solves the problem with training neural networks or ...
2
votes
0answers
47 views

Recommendations on which architecture to use to guess appointment

I'm currently developping an application which allows psychologists to manage their schedule and budget. As a proof of concept, I would like to create an intelligent appointment service. There can be ...
4
votes
1answer
144 views

A good way to understand the mathematical details of variational autoencoders through implementation?

As a researcher, I am getting interested in deep learning (as everyone else:)), and I decided to start with the variational eutoencoders, since I am more interested in unsupervised than supervised ...
3
votes
0answers
175 views

Is iLQG a good algorithm for model-based planning with simple environments?

In their work Continuous Deep Q-Learning with Model-based Acceleration, the author demonstrate great results of applying Imagination Rollouts for model-based acceleration of learning. They test their ...
3
votes
0answers
47 views

Loss of precision when encoding DNN weights

This question is related to the usage of NN in critical systems (those where a failure can cause life threatening situations - autopilots for example) and the need for formal guarantees on their ...
3
votes
0answers
210 views

Can anybody explain such behavior of accuracy and loss of my Net(caffe)?

I used this project for example(framework - caffe, arhitecture of net - mod of AlexNet, 400 images are used for training). I have this result: or this: Solver: ...
5
votes
1answer
674 views

Using crowdsourcing for deep learning

Most companies dealing with deep learning (automotive - Comma.ai, Mobileye, various automakers etc.) do collect large amounts of data to learn from and then use lots of computational power to train a ...
4
votes
3answers
281 views

Can someone direct me to a sites and/or videos that can bring an absolute beginner up to speed with AI? [closed]

To start, I'm not a programmer/computer scientist/et al... - I work in Finance and have, through my job, self-thought myself VBA for excel and outlook and would consider myself as being in the upper ...
2
votes
0answers
104 views

Categorical Variable Reduction using NN

I was trying to categorical variable engineering following this paper. The code is the following: ...
3
votes
2answers
118 views

Is a deep technical understanding of neural networks required outside of research?

To understand the inner workings of neural networks, a fair amount of mathematical concepts is required. Backpropagation alone is a challenging technique if you are not fluent in calculating local ...
1
vote
0answers
48 views

Neural Network to Interpolate Matrices

I am considering some possibilities to improve a Variable Gain nonlinear control system. One of the drawbacks of the current technique is that the change of the gains is discrete and the switching ...
3
votes
1answer
1k views

Image Recognition and Orientation Detection

Hypothetically, the symbol (Triangle) is sticked to an item and i need to find and recognize that symbol and try to calculate the orientation of the item it is sticked into. In degrees. How would you ...
2
votes
3answers
4k views

When using neural networks to detect features in an image, how can locate that specific feature in the original image?

I understand how a neural network can be trained to recognise certain features in an image (faces, cars, ...), where the inputs are the image's pixels, and the output is a set of boolean values ...
1
vote
1answer
82 views

debugging perceptron for digital AND circuit

I was trying to code a single layer perceptron to understand binary AND: 1 1 1 0 1 0 1 0 0 0 0 0 I made up this code ...
4
votes
1answer
158 views

Can a neural network learn to avoid wrong decisions using backpropagation?

I studied the articles on Neural Networks and Deep Learning from Michael Nielsen and developed a simple neural network based on his examples. I understand how backpropagation works and I already ...
11
votes
3answers
159 views

How can I make my network treat rotations of the input equally?

I'm attempting to program my own system to run a neural network. To reduce the number of nodes needed, it was suggested to make it treat rotations of the input equally. My network aims to learn and ...
2
votes
2answers
242 views

Neural Network example

I read a lot about this, I understand how it work, but I would like the most simple example you can provide me, because I have no clue how I would make it in code. No matter the language( I would ...
5
votes
3answers
602 views

Use of machine learning for analyzing companies enlisted in stock market

Can current trends and tools, in the field of machine learning, replicate the complexity of financial market? If yes, then what are the tools available in this domain. Q. I am trying to build a model ...
1
vote
3answers
798 views

Ensemble Learning using Convolutional Neural Networks

I have created 22 different Convolutional neural networks that all test for the presence of unique objects in an image (each one of the classifiers is unique). Each sample in the test set has the ...
1
vote
1answer
235 views

Comments on my proposed "Jitter" neuron

I have an application of neural networks (standard MLP architecture) where I want to forecast a tanh output (ranging from -1 to +1) with about 1500 input features in ~700 samples. Each sample ...
1
vote
1answer
136 views

Successful methods for optical character recognition?

Alright, I want to write a mobile app that lets you take a photo of your equation, detects the equation, transforms it from pixels to text and then solves if it's possible. Right now, I am doing the ...
1
vote
1answer
504 views

What are the criteria for choosing Turing award winners? [closed]

Why does not a researcher like Geoffrey Hinton with his valuable works in machine learning (especially neural networks) get Turing award?
2
votes
0answers
122 views

Train, Validation and Test Split for Reporting Accuracy of Neural Model and BOW

I need to report accuracies of my neural model in a conference paper as compared to various baselines. What are the accepted standards for reporting accuracies in a fair manner? Neural Model: To be ...
3
votes
2answers
2k views

Is it illegal to use pictures of public figures to train a neural network?

I want to train a neural network with pictures of public figures (politicians, singers, etc), but I do not know if it's legal, I do not plan to show them in my project I only want to use them to train ...
2
votes
0answers
70 views

seq2seq vector to letters model

I'm looking to build a sequence-to-sequence model that takes in a 2048-long vector of 1s and 0s as my input and translating it to my known output of (a variable length) 1-20 long characters (ex. ...
10
votes
2answers
2k views

Can autoencoders be used for supervised learning?

Can autoencoders be used for supervised learning without adding an output layer? Can we simply feed it with a concatenated input-output vector for training, and reconstruct the output part from the ...
0
votes
2answers
198 views

Programming Collective Intelligence

Is Programming Collective Intelligence by Toby Segaran a good book to enter in the AI and neural networks world for a novice?
2
votes
1answer
2k views

Multi-label Classification with non-binary outputs [closed]

I am looking to train a dataset that would output a sequence of letters (I'm using this for peptide sequences). Since I have 22 different possibilities of amino acids, I need to output a vector that ...
9
votes
1answer
269 views

How powerful are the computers that power the most advanced artificial intelligence nowdays

How powerful is the machine that beat the poker player champion recently?
0
votes
2answers
202 views

How can object types be differentiated in the input of a neural network?

In a neural network when inputting nerve input to sense a 2D environment, how do you differentiate two types of objects (with similar shape and size) so the neural network can treat them differently? ...
5
votes
1answer
173 views

Is it feasible to train a Machine Learning Model (with image inputs) in an average personal computer?

There are lots of examples of machine learning systems that can recognize objects and extract other information from images with very high precision. To train the models of such systems is necessary (...
2
votes
2answers
1k views

Why are inhibitory connections often used in virtual neural networks when they don't seem to exist in real life neural networks?

Something I like about neural network AI is that we already have a blueprint for it - we know in great detail how different types of neurons work, and we don't have to invent the AI, we can just ...
2
votes
1answer
693 views

How can I use deep neural networks to recognize characters on vehicle license plate? [closed]

I was able to extract the license plate from a given car image, using Matlab. I would like to use deep neural networks to recognize the characters on the plate now. How can i proceed further? I don't ...
9
votes
2answers
518 views

Was DeepMind's DQN Atari game learning simultaneous?

DeepMind state that their deep Q-network (DQN) was able to continually adapt its behavior while learning to play 49 Atari games. After learning all games with the same neural net, was the agent ...
0
votes
1answer
171 views

How to deal with changing video frame sizes in a CNN?

How to deal with videos where the frame sizes are not the same frame to frame? For example this video moves up and down and when it does, the video part of the screen has a different amount of pixels ...
3
votes
1answer
122 views

What linear rectifier is better?

What rectifier is better in general case of Convolutional Neural Network and how about empirical rules to use each type? ReLU PReLU RReLU ELU Leacky ReLU
1
vote
1answer
137 views

How should dropout change with network depth?

I know I've seen this somewhere before, but can't find it now. Say we have a neural network with a handful of layers, and we're applying dropout to each layer. As we move closer to the output, ...
2
votes
4answers
432 views

Training neural network for good taste in art

I'm a newbie in machine learning, so excuse me in advance). I have an idea to make NN that can estimate visual pleasantness of arbitrary image. Like you have a bunch of images that you like, you train ...
1
vote
2answers
135 views

Is there a "better" (signal-based) language for artificial intelligence [closed]

I assume, there must be "signal-driven" and maybe also real-time programming language, which based on connectivy-data more than variables (int, string, etc). I would like to have a language without ...
3
votes
1answer
202 views

Can we apply ANN to cryptography?

If a group of computers have identical ANN with exact same set of learning data and all have functionality of encryption and decryption, would there be any way for interceptors to interpret encrypted ...
2
votes
1answer
115 views

Recognition of abbreviated text

I want to write a program that looks at abbreviated words, then figures out what the words are. For example, the abbreviation is "blk comp", and the translation is "black computer". In order to give ...
3
votes
1answer
698 views

Detect street and sidewalk surface in aerial imagery (neural network)

I would like to detect street and sidewalk surface in a very detailed (0.075m/pix) USGS High Resolution Orthoimagery which basically means image segmentation with two classes. Places in question are ...
3
votes
2answers
9k views
1
vote
0answers
64 views

Can a CNN or MLP discover similar but untrained-on patterns?

I've been experimenting with a simple tic-tac-toe game to learn neural network programming (MLP and CNNs) with good results. I train the networks on a board positions and the best moves and the ...
4
votes
1answer
88 views

Why do neural networks based AI players still require extensive search techniques?

Today we have neural network based AI players that are comparable or better than humans in games that require extensive pattern matching and "intuition". AlphaGo is a prime example. But these AI ...
2
votes
0answers
141 views

Creating a neural network for predicting next vote in a series of votes [closed]

We are working on a project for creating music based on crowd sourcing. People vote for every note until the vote is closed, and then move on to the next vote until the canvas for the music is filled. ...
5
votes
1answer
780 views

How does visual cortex share convolution weight

TL;DR If we buy into the idea visual cortex functions like a convolutional neural network, then there's a problem makes me scratch my head: how does brain force weight sharing as in convolutional ...
3
votes
1answer
58 views

Would a neuromorphic SNN of the same complexity as the human nervous system be 'smarter'?

If the nervous system is wired up such that there are no well defined layers, how does this compare to a neatly stacked artificial net? If between my sensory and motor side I had a neatly designed SNN ...