48 votes
Accepted

Why is Python such a popular language in the AI field?

Python comes with a huge amount of inbuilt libraries. Many of the libraries are for Artificial Intelligence and Machine Learning. Some of the libraries are TensorFlow (which is a high-level neural ...
  • 2,023
37 votes
Accepted

What are "bottlenecks" in neural networks?

The bottleneck in a neural network is just a layer with fewer neurons than the layer below or above it. Having such a layer encourages the network to compress feature representations (of salient ...
  • 26.6k
35 votes
Accepted

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

The concept you are looking for is called epistemic uncertainty, also known as model uncertainty. You want the model to produce meaningful calibrated probabilities that quantify the real confidence of ...
  • 1,112
15 votes
Accepted

How to classify data which is spiral in shape?

There are many approaches to this kind of problem. The most obvious one is to create new features. The best features I can come up with is to transform the coordinates to spherical coordinates. I ...
15 votes

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

Your classifier is specifically learning the ways in which 0s are different from other digits, not what it really means for a digit to be a zero. Philosophically, you could say the model appears to ...
13 votes
Accepted

Is there a machine learning model that can be trained with labels that only say how "right" or "wrong" it was?

What you are looking for is called "reinforcement learning". A reinforcement learning algorithm will try to maximize a reward function. This reward represents how "good" or "...
  • 424
11 votes

What are "bottlenecks" in neural networks?

Imagine, you want to re-compute the last layer of a pre-trained model : Input->[Freezed-Layers]->[Last-Layer-To-Re-Compute]->Output To train [Last-...
  • 111
10 votes

How to train a neural network for a round based board game?

Great question! NN is very promising for this type of problem: Giraffe Chess. Lai's accomplishment was considered to be a pretty big deal, but unfortunately came just a few months before AlphaGo ...
  • 6,177
9 votes

How to classify data which is spiral in shape?

Ideally neural networks should be able to find out the function out on it's own without us providing the spherical features. After some experimentation I was able to reach a configuration where we do ...
9 votes

Why is Python such a popular language in the AI field?

What attracts me to Python for my analysis work is the "full-stack" of tools that are available by virtue of being designed as a general purpose language vs. R as a domain specific language. The ...
9 votes

Can LSTM neural networks be sped up by a GPU?

From Nvidia www (https://developer.nvidia.com/discover/lstm): Accelerating Long Short-Term Memory using GPUs The parallel processing capabilities of GPUs can accelerate the LSTM training and ...
9 votes
Accepted

How fast is TensorFlow compared to self written neural nets?

I wanted to know how the performance of my net would be compared to the same in Tensor Flow. Not to specific but just a rough aproximation. This is very hard to answer in specific terms because ...
  • 210
9 votes
Accepted

How to use CNN for making predictions on non-image data?

You can use CNN on any data, but it's recommended to use CNN only on data that have spatial features (It might still work on data that doesn't have spatial features, see DuttaA's comment below). For ...
  • 2,621
8 votes

Why is Python such a popular language in the AI field?

Python has a standard library in development, and a few for AI. It has an intuitive syntax, basic control flow, and data structures. It also supports interpretive run-time, without standard compiler ...
7 votes

How to train a neural network for a round based board game?

I'm a chess player and my answer will be only on chess. Training a neural network with reinforcement learning isn't new, it has been done many times in the literature. I'll briefly explain the common ...
  • 1,411
7 votes
Accepted

Is a GPU always faster than a CPU for training neural networks?

This changes according to your data and complexity of your models. See following article by microsoft. Their conclusion is The results suggest that the throughput from GPU clusters is always ...
7 votes

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

Broken assumptions Generalization relies on making strong assumptions (no free lunch, etc). If you break your assumptions, then you're not going to have a good time. A key assumption of a standard ...
  • 873
6 votes

How to use CNN for making predictions on non-image data?

The convolutional models are a method of choice when your problem is translation invariant (or covariant). In image classification, the image should be classified into class 'cow' if a cow is present ...
  • 489
6 votes
Accepted

Why isn't my Neural Network based calculator working?

A neural network is not good at selecting a function based on those 3 input parameters, because of the way a neuron is setup. What you should do is either make a neural network for each operation, or ...
6 votes

How to embed/deploy an arbitrary machine learning model on microcontrollers?

There are a few possible approaches to deploying a ML model to a microcontroller. The main limiting factor to deployment on microcontollers is that ML models are usually a representation of a set of ...
5 votes

How to classify data which is spiral in shape?

By cheating... theta is $\arctan(y,x)$, $r$ is $\sqrt{(x^2 + y^2)}$. In theory, $x^2$ and $y^2$ should work, but, in practice, they somehow failed, even though, ...
5 votes
Accepted

Can LSTM neural networks be sped up by a GPU?

I found that there are cuDNN accelerated cells in Keras, for example, https://keras.io/layers/recurrent/#cudnnlstm. They are very fast. The normal LSTM cells are faster on CPU than on GPU.
  • 279
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. ...
5 votes
Accepted

Has anyone been able to solve OpenAI's hardcore bipedal walker with their implementation of DDPG?

You may be very interested to know that there was a bug in the v2 Lidar tracing, making the agent think there were phantom objects, and sometimes intersecting with its own legs: https://github.com/...
5 votes
Accepted

Do we have anything like accuracy and loss in RNN models?

RNN's stand for Recurrent Neural Networks which is, in fact, Deep Learning. There has to be a loss since you're dealing with supervised learning and the typical loss metrics used are the same as you ...
  • 1,379
4 votes

Why is Python such a popular language in the AI field?

It's a mix of many factors that together make it a very good option to develop cognitive systems. Quick development Rapid prototyping Friendly syntax with almost human-level readability Diverse ...
  • 141
4 votes

How to train a neural network for a round based board game?

I think you should get familiar with reinforcement learning. In this field of machine learning the agent interacts whit its environment and after that the agent gets some reward. Now, the agent is the ...
4 votes
Accepted

Can I build a CNN for image classification tasks just with OpenCV?

OpenCV does include 2D filter convolution functions for custom separable and non-separable filters. The latter uses DFT for large filters, which may or may not be faster than the conventional method. ...
4 votes
Accepted

Accuracy too high too fast?

It actually depends on a couple of things here - How many output classes do you have? If you have only 2 or 3 classes, it is a very easy task for the classifier that you have built. So, it is highly ...

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