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
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 ...
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.
8
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, ...
7
There is stuff like the Universal Approximation Theorem.
There are also investigations into the loss surface of neural networks.
And classics like this explanation of the vanishing gradient problem.
But I'm afraid the mathematical theory of neural networks only exists in bits and pieces in many different papers. And many of the most important questions ...
7
A simple form of sarcasm involves a direct reversal of the literal meaning of the statement, eg "Great weather we're having" (during a thunderstorm), "just what I needed" (when something goes wrong).
The problem with doing this in random sentences is that you may have no context to establish the reversal of the literal meaning.
You could possibly construct ...
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 ...
7
Although I have only partially read (or not read at all) some of the following resources and some of these resources may not cover more advanced topics than the ones presented in the book you are reading, I think they can still be useful for your purposes, so I will share them with you.
I would also like to note that if you understand the contents of the ...
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
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
Traditionally,, 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 permutations to the network such ...
5
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, ...
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
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
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 ...
5
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 ...
5
Yes, there are many, actually. A Google search turned this paper Artificial Neural Networks in Medical Diagnosis (2011) by Al-Shayea up.
Not only are they used in disease diagnosis, but even with things like prescribing medicines. In fact, the top project for a hackathon at my school analysed thousands of research articles, and took a patient's medication ...
5
If you're interested in the theory behind Double Q-learning (not deep!), the reference paper would be Double Q-learning by Hado van Hasselt (2010).
As for Double deep Q-learning (also called DDQN, short for Double Deep Q-networks), the reference paper would be Deep Reinforcement Learning with Double Q-learning by Van Hasselt et al. (2016), as pointed out ...
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
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 ...
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
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
The paper The role of artificial intelligence in achieving the Sustainable Development Goals (2020, published in Nature) should contain the information you're looking for.
In the introduction, the authors write
Here we present and discuss implications of how AI can either enable or inhibit the delivery of all 17 goals and 169 targets recognized in the ...
4
[Disclaimer: I work for a company that provides a platform for developing conversational AI systems]
The platform used by the company I work for has a sentiment analysis component, so you can recognise if the user input expresses certain emotions. The dialogues are encoded in 'flows', which are graphs with an initial trigger consisting of output nodes and ...
4
There are actually quite a few. Personally I would say these courses have high quality and strong focus on practice:
Standford computer vision cs231. Check the assignments materials on this page. This course has good explanation/exercises of how generally neural nets and backprop works.
Fastai course notebooks. You can listen to the lectures as well, but ...
4
The book Grokking Deep Learning, by Andrew Trask (a PhD student at Oxford University and a research scientist at DeepMind), a wonderful, clean, and plain-English discussion of the basic mechanics that go on under the hood of neural networks - from data flow to updating of weights. It is written without a slant on normally-wonky math, the concepts are ...
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 ...
Only top voted, non community-wiki answers of a minimum length are eligible
