27
Yes, there is some research on this topic, which can be called adversarial machine learning, which is more an experimental field.
An adversarial example is an input similar to the ones used to train the model, but that leads the model to produce an unexpected outcome. For example, consider an artificial neural network (ANN) trained to distinguish between ...
12
Sometimes if the rules used by an AI to identify characters are discovered, and if the rules used by a human being to identify the same characters are different, it is possible to design characters that are recognized by a human being but not recognized by an AI. However, if the human being and AI both use the same rules, they will recognize the same ...
10
Yes there are, for instance one pixel attacks described in
Su, J.; Vargas, D.V.; Kouichi, S. One pixel attack for fooling deep
neural networks. arXiv:1710.08864
One pixels attacks are attacks in which changing one pixel in input image can strongly affect the results.
7
Douglas Hofstadter's CopyCat architecture for solving letter-string analogy problems was deliberately engineered to maintain a semantically-informed notion of 'salience', i.e. given a variety of competing possibilities, tend to maintain interest in the one that is most compelling. Although the salience value of (part of) a solution is ultimately represented ...
6
You could say that NAS fits into the domain of Meta Learning or Meta Machine learning.
I've pulled the NAS papers from my notes, this is a collection of papers/lectures that I personally found very interesting. It's sorted in rough chronological descending order, and *** means influential / must read.
Quoc V. Le and Barret Zoph are to good authors on the ...
5
There's Neural Program Synthesis, which can be used to generate a piece of code. Please, have a look at the article Neural Program Synthesis by Microsoft for an overview of the field.
5
I think that the answer to your question is yes. In the article New A.I. application can write its own code, the authors state
Computer scientists have created a deep-learning, software-coding application that can help human programmers navigate the growing multitude of often-undocumented application programming interfaces, or APIs.
Designing ...
5
Here is a few that might be what you are looking for:
Deep Sets, https://papers.nips.cc/paper/6931-deep-sets.pdf
BRUNO: A Deep Recurrent Model for Exchangeable Data, https://arxiv.org/pdf/1802.07535.pdf
Deep Learning with Sets and Point Clouds, https://openreview.net/pdf?id=HJF3iD9xe
Permutation-equivariant neural networks applied to dynamics prediction, ...
5
Concentration, perhaps easier to grasp as "focus" or "attention", has quite some history in AI. This answer mentions CopyCat, and there was work with neural networks in the 80s as well (e.g. from Fukushima, creator of the Neocognitron).
More recently, attention in neural networks is gaining momentum. The mechanisms are applied to learning in deep neural ...
5
Here's an example:
How to hack your face to dodge the rise of facial recognition tech
In his recent book The Fall, Stephenson wrote about smartglasses that that project a pattern over the facial features to foil recognition algorithms (which seems not only feasible but likely;)
Here's an article from our sponsors, Adversarial AI: As New Attack Vector ...
4
In addition to the books already mentioned, I would like to recommend to you some that helped me understand the basics and guided me through my first AI / CI implementations.
Computational Intelligence: An Introduction by Andries P. Engelbrecht
It includes the most relevant developments in computational intelligence with good discussions on intelligence ...
4
There are several generative models that have been proposed before or roughly at the same time of the GAN (2014). For example, the deep Boltzman machine (2009), deep generative stochastic network (2014) or variational auto-encoder (2014).
4
There are several papers related to the topic, because there have been several attempts to show this from slightly different perspectives and using slightly different assumptions (e.g. assuming that certain activation functions are used).
The article A visual proof that neural nets can compute any function (by Michael Nielsen) should give you some intuition ...
4
Isn't that essentially what chess does? For example, A human can recognize that a Ruy exchange offers white great winning chances (because of pawn structure) by move 4 while an engine would take several hours of brute force calculation to understand the same idea.
4
There are many insightful comments and answers so far. I want to illustrate my idea of "color blindness test" more. Maybe it's a hint to lead us to the truth.
Imagine there are two people here. One is colorblind (AI) and another one is non-colorblind (human). If we show them a normal number "6", both of them can easily recognize it as number 6. Now, if we ...
4
The following articles
Ising models for networks of real neurons (2006) by Gasper Tkacik et al.
Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models (2018) by Kyle Mills et al.
Inverse Ising inference by combining Ornstein-Zernike theory with deep learning (2017) by Soma Turi, Alpha A. Lee et al.
...
4
Introduction
The paper Generalization in Deep Learning provides a good overview (in section 2) of several results regarding the concept of generalisation in deep learning. I will try to describe one of the results (which is based on concepts from computational or statistical learning theory, so you should expect a technical answer), but I will first ...
3
I have implemented Permutational Layer here using Keras: https://github.com/off99555/superkeras/blob/master/permutational_layer.py
You can call the PermutationalModule function to use it.
Implemented following this paper:
https://arxiv.org/pdf/1612.04530.pdf
The idea is to compare all pairs of N^2 pairs from N inputs, use the model with shared weights, ...
3
One of the important qualifications of the Universal approximation theorem is that the neural network approximation may be computationally infeasible.
"A feedforward network with a single layer is sufficient to represent any function, but the layer may be infeasibly large and may fail to learn and generalize correctly." - Ian Goodfellow, DLB
I can't ...
3
There's not really a good textbook yet, but there are more resources than I expected for this topic, so I'll list them as an answer here:
MIT offers a course in this. The slides and lecture videos are up online. It looks fairly speculative to me, and perhaps more application-focused than what was asked for.
There is actually a book called Artificial General ...
3
Nice Question!
This is a perennial topic of discussion among AI researchers. The short answer is "we don't really know which topics are hard in general, but we do know which we haven't got good techniques for yet."
Let's start by explaining why AI is not concerned with notions of computational complexity like NP-Completeness. AI researchers figured out in ...
3
For a foundation, there is nothing better than Cybernetics by Norbert Wiener. It is surprising how advanced this MIT professor was, prior to Turing's thought experiment on a general purpose computing machine or the embodiment of the von Neumann architecture upon which most contemporary computers are based. In key ways his analysis of time series and ...
3
Here's a live demo: https://www.labsix.org/physical-objects-that-fool-neural-nets/
Recall that neural nets are trained by feeding in the training data, evaluating the net, and using the error between the observed and the intended output to adjust the weights and bring the observed output closer to the intended. Most attacks have been on the observation that ...
3
Is the image taken from a constant distance?
If yes, you'd need to scale the images to the same dimensions first of all. For few images say 100-500 images (more the better) you'd need to label the dataset by proper scaling.
Once labeled, use it to train a CNN (Although best would be training a ResNet). Once trained with decent accuracy, test it for the ...
3
One of the methods which is quite fast and easy to implement.
You can do Principal Component Analysis (PCA) based face recognition. You can go through this paper for the theory behind it. For an example implementation you can see this blog post.
The process, roughly, is as following:
If you have a grayscale image of size $(20,20)$, then this image can be ...
3
As far as I know, no true artificial general intelligent system (AGI) has been implemented or is practically useful. Yes, there is Sophia and similar robots that may look like an AGI, but they aren't really AGI systems, as they lack several capabilities that we humans have and they can't really adapt to new circumstances. AlphaGo and AlphaStar are narrow AI ...
2
A parallel situation might be that of spam/not spam. The detection of spam by AI has been pretty successful, so there is an existing algorithm - classification. However while you have a possible approach you are still missing the key ingredient which is sufficient data to train the model on.
AI depends on a large amount of data to train the model. Ideally ...
2
Yes, there are a couple of ways to apply reinforcement learning in computer vision problems. This mainly employs the principle of "applying the algorithm -> evaluating the outcome -> adopting the best outcome".
The following are a couple of examples that use reinforcement learning in computer vision.
CAD2RL: Real Single-Image Flight Without a Single
Real ...
2
As far as I know, no one has tried this, due to the way the network is structured. Each input has a set of weights, that are connected to more inputs. If the inputs switch, the output will too.
However, you can build a network that approaches this behaviour. In your training set, use batch learning and for each training sample, give all possible ...
2
Firstly, you should be clear about on which subject you want to study.
AIMA deals with conventional ai algorithms like path planning, logic etc.
Elements of statistical learning is a machine learning book which covers most of the machine learning algorithms you will come across (spare deep learning).
digital image processing is an entirely different field ...
Only top voted, non community-wiki answers of a minimum length are eligible
