7
votes
Why not teach to a NN not only what is true, but also what is not true?
Yes this is done routinely. For example this is how the YOLO object detection and classifier system works, to give a real-world for example. In YOLO, the "non-object" classification is "background" i....
- 32.1k
4
votes
Accepted
Where do 'random seeds' get used in deep neural networks?
I suppose the most common part where it will be used is in the initialization of weights before training; the best ways currently known to do that involve randomness.
If you use Dropout during ...
- 10.3k
4
votes
Accepted
Is a decision tree less suitable for incremental learning than e.g. a neural net?
I will try to answer all three questions to the best of my ability.
Is this basically true? Quick googling just brought me to a lot of papers trying to fit decision trees into incremental learning.
...
- 153
3
votes
Accepted
Which learning algorithms are suitable for data leakage detection and prevention?
This seems to fall broadly into the regime of a classification problem as you want to classify an outgoing communication as "contains proprietary information" or "does not contain proprietary ...
- 3,757
3
votes
How do you interpret this learning curve?
The validation loss settles exactly at an error of one. Probably means there's something off with either the kind of data validation set has or with something in the training. An exact validation loss ...
- 1,409
3
votes
How do you interpret this learning curve?
Depends on what does 1 represent in your task.
If you are trying to predict household prices and 1 represents \$1, I think the average validation loss is good. If 1 represents \$10000 in this case, ...
- 81
3
votes
Accepted
What is the difference between a learning algorithm and a hypothesis?
In computational learning theory, a learning algorithm (or learner) $A$ is an algorithm that chooses a hypothesis (which is a function) $h: \mathcal{X} \rightarrow \mathcal{Y}$, where $\mathcal{X}$ is ...
- 40.5k
2
votes
Accepted
What is the proof behind the gradient of a curve being proportional to the distance between the two co-ordinates in the x-axis?
Don’t think about it as the $w_{(n)}-w_{(n+1)}$ being proportional to something. Think about it this way:
I'm now at $w_{(n)}$. Where do I want to be at timestep, so that the error decreases? For that,...
- 136
2
votes
Accepted
Trading off "Memory" vs "Optimization"
The The Oxford Companion to Chess has entries on only 700 named openings, and lists another 1327 opening variations in the index, and I wouldn't be surprised if someone out there had them all ...
- 6,227
2
votes
Trading off "Memory" vs "Optimization"
If you can remember everything and there's no randomisation in your outcome like chess, there is absolutely no reason not to do that. Anybody who can remember all the possible board configurations in ...
- 1,411
2
votes
Accepted
Approaches to an algorithm for crossing a road
Any AI algorithm depends on the environment, and available actuators and sensors. In our case, the environment is a road, street, etc. The primary actuator includes wheels (or legs) of the robot. ...
- 2,023
2
votes
Why do Decision Tree Learning Algorithm preferably outputs the smallest Decision Tree?
Adding to SmallChess's answer ,
Larger trees(with many nodes) are too adapted to the training set, as a small change in the input train data might cause the trees to change very much and hence change ...
- 181
2
votes
Why do Decision Tree Learning Algorithm preferably outputs the smallest Decision Tree?
The bigger your tree is the more overfitting your model is. In machine learning, we always prefer a simpler model unless there is good reason to go for complication.
- 1,411
2
votes
Accepted
How can artificial intelligence (including deep learning algorithms) find suspicious patterns in the body’s biochemistry?
I wouldn't focus only on "deep learning" unless you have some specific reason for doing so. There may be other techniques which could be as effective, or more effective.
One approach I've seen ...
- 3,757
2
votes
In the multi-linear regression, how is the value of weight $b_2$ calculated?
It is calculated the same way $b_1$ is calculated.
Nearly following your notation, say your multiple linear regression function is
$H(X_i) = b_0 + b_1x_{1,i} + ...+ b_nx_{n, i}$
for data ...
- 823
2
votes
Accepted
Does a solution for Wumpus World with neural networks exist?
Yes! If you read ahead to the chapters in reinforcement learning in the same book, you'll see that the wompus world appears again there. Techniques like Q-learning can be used to solve it, and since Q-...
- 9,257
2
votes
Can we define the AI singularity mathematically?
I found someone that has done this thing! You can hear a good explanation in Marcus Hutter's answer to this question about rewards given to AIXI. He describes a work that seems to be referring to this ...
- 274
2
votes
Accepted
Is it possible to do K-nearest-neighbours before training DNN
There are two factors that will change the ability of a deep neural network to fit a given dataset: either you need more data, or a deeper and wider network. Since the pattern is only 2-d, it can ...
- 9,257
2
votes
Accepted
Why does the machine learning algorithm need to learn a set of functions in the case of missing data?
Intuitively, this is similar to the case when you are making predictions but you don't have all the necessary information to make the most accurate prediction or maybe there isn't a single accurate ...
- 40.5k
2
votes
Why does the machine learning algorithm need to learn a set of functions in the case of missing data?
@The Pointer the $2^n$ came from the question: How many function do we need to have if each of the $n$ inputs can be missing?
example: $f_1(\text{missing}, x_2, x_3, \dots, x_n)$ for $x_1$ missing
$...
2
votes
Accepted
What is the borderline between unsupervised learning and regular algorithms?
Any algorithm that uses data (in some form) to improve some performance measure (aka objective function), or to find some function, can be considered a machine learning algorithm. See this answer for ...
- 40.5k
1
vote
How do you interpret this learning curve?
The telltale signature of overfitting is when your validation loss starts increasing, while your training loss continues decreasing, i.e.:
(Image adapted from Wikipedia entry on overfitting)
It is ...
- 1,044
1
vote
Using ML to analyze Facebook posts
for this kind of ml training, you will need a ton of data first, at least in the thousands. If you have a bot program that fetches those data for you, AI is the way to go. I'm not sure how else you ...
- 149
1
vote
Use AI to auto-correlate the words of human-translated texts?
You are basically describing the way Google Translate works.
There has been a lot of research in text alignment in the area of multi-lingual corpus linguistics. An early paper (with sourcode) is Gale ...
- 5,387
1
vote
Can we define the AI singularity mathematically?
Here is one idea. I'll start with a more specific "mathematical singularity", defined as an algorithm that can do the following in N hours or less (for all $N >= 1$):
State equivalent versions (up ...
- 274
1
vote
What is the approach to deduce formal rules based on data?
If you don't have non-examples of your pattern and don't have some kind of heuristic guide, unfortunately the answer is that you can't. "All sentences" will always be 100% compatible with your ...
- 301
1
vote
What's an appropriate algorithm for classification with categorical features?
What you have is called a classification problem with categorical features. That is, the features can be represented numerically, but the numbers have no relative meaning.
Algorithms that rely on ...
- 9,257
1
vote
Teaching a NN to manipulate pseudoRNG over a long time scale?
The point of pseudoRNG is to be unmodable and unpredictable, making it hard to train an AI to learn. It would more likely be useful and more efficient to have the equation that the game uses for ...
- 111
1
vote
Which machine learning algorithm is suitable for detecting text w.r.t set of words
If your main issue is dealing with new vocabulary, you could try using a parts-of-speech tagger as a pre-processing step. You would then effectively discover relationships between "noun" and "verb", ...
- 5,387
1
vote
Accepted
Which is best: evaluation of states or probability of moves?
Which do you think is the best method?
As with most machine learning, each approach has its strengths and weaknesses, and other than a little bit of intuition:
Policy-based methods are strong in ...
- 32.1k
Only top scored, non community-wiki answers of a minimum length are eligible