Skip to main content
62 votes
Accepted

How is it possible that deep neural networks are so easily fooled?

First up, those images (even the first few) aren't complete trash despite being junk to humans; they're actually finely tuned with various advanced techniques, including another neural network. The ...
Ben N's user avatar
  • 2,609
29 votes

How is it possible that deep neural networks are so easily fooled?

The images that you provided may be unrecognizable for us. They are actually the images that we recognize but evolved using the Sferes evolutionary framework. While these images are almost impossible ...
Vishnu JK's user avatar
  • 1,082
29 votes
Accepted

Is there any research on the development of attacks against artificial intelligence systems?

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 ...
nbro's user avatar
  • 41k
23 votes
Accepted

How do I handle large images when training a CNN?

How do I handle such large image sizes without downsampling? I assume that by downsampling you mean scaling down the input before passing it into CNN. Convolutional layer allows to downsample the ...
Maxim's user avatar
  • 1,967
17 votes

How is it possible that deep neural networks are so easily fooled?

All answers here are great, but, for some reason, nothing has been said so far on why this effect should not surprise you. I'll fill the blank. Let me start with one requirement that is absolutely ...
Maxim's user avatar
  • 1,967
13 votes

Is the pattern recognition capability of CNNs limited to image processing?

Convolutional Nets (CNN) rely on mathematical convolution (e.g. 2D or 3D convolutions), which is commonly used for signal processing. Images are a type of signal, and convolution can equally be used ...
Eric Platon's user avatar
  • 1,510
12 votes

Is there any research on the development of attacks against artificial intelligence systems?

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 ...
S. McGrew's user avatar
  • 363
11 votes

How is it possible that deep neural networks are so easily fooled?

An important question that does not yet have a satisfactory answer in neural network research is how DNNs come up with the predictions they offer. DNNs effectively work (though not exactly) by ...
Harsh's user avatar
  • 1,325
11 votes

Is there any research on the development of attacks against artificial intelligence systems?

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 ...
internetofmine's user avatar
7 votes
Accepted

How many neurons would a network have after a training of 100k small images?

The neural network is typically a set size once it's created. You'd have to create a network big enough for your data-set.
Zakk Diaz's user avatar
  • 366
7 votes
Accepted

How much of a problem is white noise for the real-world usage of a DNN?

The white noise that fools DNNs isn't really white noise. It has been altered in the same way as the synthetic misclassified pictures have been altered. You have to change many input pixels in exactly ...
BlindKungFuMaster's user avatar
7 votes

How do I handle large images when training a CNN?

Usually for images the feature set is the pixel density values and in this case it will lead to quite a big feature set; also down sampling the images is also not recommended as you may lose (actually ...
Karan Chopra's user avatar
6 votes
Accepted

Can a single neural network handle recognizing two types of objects, or should it be split into two smaller networks?

Well, I do not know what type of features you are giving to your neural network. However, in general, I would go with a single neural network. It seems that you have no limitation in resources for ...
Didami's user avatar
  • 391
6 votes
Accepted

Are there any microchips specifically designed to run ANNs?

In May 2016 Google announced a custom ASIC which was is specifically built for machine learningwiki and tailored for TensorFlow. It is using tensor processing unit (TPU) which is a programmable ...
kenorb's user avatar
  • 10.5k
6 votes
Accepted

Is the QuickDraw with Google neural net a convolutional neural network?

I believe they don't use CNNs. The most important reason why it's because they have more information than a regular image: time. The input they receive is a sequence of (x,y,t) as you draw on the ...
etal's user avatar
  • 176
6 votes

Cropping image using ML?

Yes, this is possible. There is actually a pretty easy way that doesn't even require machine learning and can be implemented with a small amount of code. You just use a framework for image processing ...
Demento's user avatar
  • 1,684
5 votes
Accepted

How can action recognition be achieved?

There are several approaches as to how this can be achieved. One recent study from 2015 about Action Recognition in Realistic Sports VideosPDF uses the action recognition framework based on the three ...
kenorb's user avatar
  • 10.5k
5 votes

How can action recognition be achieved?

This study from 2012 uses 3D convolutional neural networks (CNN) for automated recognition of human actions in surveillance videos. The 3D CNN model extracts features from both the spatial and the ...
kenorb's user avatar
  • 10.5k
5 votes

Is the pattern recognition capability of CNNs limited to image processing?

The simple answer is "no, they aren't limited to images": CNNs are also being used for natural language processing. (See here for an introduction.) I haven't seen them applied to graphical data yet, ...
Matthew Gray's user avatar
  • 4,272
5 votes

How is it possible that deep neural networks are so easily fooled?

How is it possible that deep neural networks are so easily fooled? Deep neural networks are easily fooled by giving high confidence predictions for unrecognizable images. How is this possible? Can you ...
Rob's user avatar
  • 632
5 votes
Accepted

What are the most challenging tasks aiming to achieve the lowest error rate?

Yes. Here are some of the most prominent ones and their respective state-of-the-art errors: CIFAR-10: ~3.5% error CIFAR-100: ~24% error STL-10: ~26% error SVHN: ~1.7% error ImageNet tasks: the best ...
rcpinto's user avatar
  • 2,119
5 votes
Accepted

Are there any textual CAPTCHA challenges which can fool AI, but not human?

It's an interesting question about what makes humans unique. There is a good book on the subject titled What Computers Cant Do by Hubert Dreyfus. One task that a computer can't handle (for now at ...
kvfi's user avatar
  • 116
5 votes

Are there any textual CAPTCHA challenges which can fool AI, but not human?

A method that could possibly work is utilising optical illusions such as one where two lines down a hallway are identical but one seems longer to the human eye, then they could be prompted with a ...
sgtdragonfire's user avatar
5 votes
Accepted

How good is AI at generating new, unseen [visual] examples?

We are getting pretty good at image generation, some examples: Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial ...
Franck Dernoncourt's user avatar
5 votes
Accepted

Would convolutional NN recognize patterns in encoded images?

First you should give it a try, because anyone's guess could be off, as there isn't really a complete high level analytic model of how neural networks behave on real data. Most results with neural ...
Neil Slater's user avatar
  • 32.7k
5 votes
Accepted

How are the kernels initialized in a convolutional neural network?

The kernels are usually initialized at a seemingly arbitrary value, and then you would use a gradient descent optimizer to optimize the values, so that the kernels solve your problem. There are many ...
Mustafa Radha's user avatar
5 votes
Accepted

Can machine learning algorithms be used to differentiate between small differences in details between images?

Attentive Recurrent Comparators (2017) by Pranav Shyam et al. is an interesting paper that helps to answer the question you're wondering, along with a blog post that helps to describe it in easier ...
juicedatom's user avatar
5 votes

How to detect LEGO bricks by using a deep learning approach?

So I am assuming that you are trying to detect a lego brick from the image. One idea is that you can use transfer learning. Leveraging a pre-trained machine learning model is called transfer learning. ...
Hozaifa Bhutta's user avatar
5 votes
Accepted

Is it possible to make a 'forked path' neural network?

Keras Functional APIs can help you define complex models. You can find the documentation here : https://keras.io/getting-started/functional-api-guide/. For example: ...
Sooryakiran Pallikulathil's user avatar
5 votes

Is there any research on the development of attacks against artificial intelligence systems?

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 ...
DukeZhou's user avatar
  • 6,237

Only top scored, non community-wiki answers of a minimum length are eligible