For questions about how an AI learns by itself, without being trained.
6
votes
1answer
158 views
Learning algorithms of Neural Networks
Could you please let me know which of the following classification of Neural Network's learning algorithm is correct?
The first one classifies it into:
supervised,
unsupervised and
reinforcement ...
2
votes
1answer
26 views
What techniques to explore for dynamic clustering of documents (emails)?
I have a dataset of unlabelled emails that fall into distinct categories (around a dozen). I want to be able to classify them along with new ones to come in the future in a dynamic matter. I know that ...
0
votes
0answers
16 views
Building a VAE architecture to reconstruct images
I am trying to build a VAE architecture in Lasagne which is able to reconstruct MNIST images. Note that I want to be able to sample from both the encoder and the decoder.
So far, my architecture is ...
1
vote
0answers
51 views
Kohonen clustering of flowers
I have a question about output of my SOM network.
I have trained my network with diffrent size, learning rate and epochs, but my output always can recognise two big clusters. Iris-setosa and Iris-...
1
vote
2answers
63 views
Classifying non-labeled data with high dimensionality
Disclaimer: I am a novice in the world of machine learning, so please excuse my ignorance.
My dataset consists of things like age, days since last visit, etc. This information is medical related. ...
3
votes
2answers
89 views
Can agent based machine learning achieved with any ML algorithms other than neural network?
I would like to know other tha neural network, is there any ML technique for agent based ML. If so how to train an agent with some predefined rules? Can we use python programming for representing ...
6
votes
3answers
212 views
Has anybody tried unsupervised deep learning from youtube videos?
YouTube has a huge amount of videos, many of which also containing various spoken languages. This would presumably provide something like the data that a "challenged" baby would experience - "...
0
votes
0answers
24 views
Detecting patterns in Dataset containing DB columns
How do I detect patterns in dataset containing database columns extracted from Oracle or SAS database, which R machine learning algorithms should be used for the same and from where i can get sample ...
1
vote
0answers
27 views
Learning from events. Supervised, Unsupervised or MDP?
I have a large set of simulation logs for a market simulation of which I want to learn from. The market includes:
customers
products (subscriptions)
The customers choose products and then stick with ...
3
votes
2answers
49 views
Learning in unsupervised learning
I am not clear with the concept that an unsupervised model learns. We are giving an input and output to the supervised model so that it can generate a particular value, pattern or something out of it ...
4
votes
1answer
71 views
Is it possible to write an adaptive parser?
I am working on a js library which focuses on error handling. A part of the lib is a stack parser which I'd like to work in most of the environments.
The hard part that there is no standard way to ...
3
votes
1answer
53 views
Detect observations under certain conditions
I have a customer purchasing dataset and the data set is from a retailer having an online store and offline stores. So, customers have two options in their shopping channel, online or offline. In an ...
4
votes
2answers
87 views
Predict frequently purchased items under certain conditions with customer purchasing history data
I have purchasing history data for grocery shopping. I am trying to get abnormally frequently purchased items under certain conditions. For instance, I am trying to find frequently purchased items, ...
2
votes
1answer
95 views
Keras pattern finding between hash and word
My goal is to build a neural net that can find patterns between a hash and a word on it's own. So that it returns the word of any hash that I will input.
Unfortunatally my skill in the area of ...
3
votes
1answer
67 views
K-Armed Bandit and Reinforcement Learning
In the book "Reinforcement learning" by Sutton there is a discussion of the k-armed bandit problem, where the expected reward from the bandits changes slightly over time (is non-stationary). Instead ...
3
votes
1answer
210 views
At what rate could AI theoretically self-improve?
Due to recursive self-improvement, AI could lead to an intelligence explosion improving on itself year over year exponentially.
Assuming the proper environment was created to allow an AI to self-...
3
votes
1answer
115 views
Which Reinforcement Learning algorithms are efficient for episodic problems?
I have some episodic datasets extracted from a turn-based RTS game in which the current actions leading to the next state doesn’t determine the final solution/outcome of the episode.
The learning is ...
1
vote
0answers
22 views
Does it make sense to train an autoencoder using data from different distributions?
Say I have 500 variables and I believe those variables can be shown in a 4-dimensional latent representation which I want to learn.
What I have for training is 100K samples, and those samples are ...
1
vote
1answer
61 views
How does this part of algorithm works?(K-means)
I can't understand the red box. what do does that 1 do before {c(I)=j} ?
Also how does all the algorithms work? May someone ...
5
votes
1answer
451 views
Is the new Alpha Go implementation using Generative Adversarial Networks?
I read through the publication Mastering the game of Go without Human Knowledge. It doesn't seem to use GANs, just a new form of search and reinforcement learning.
2
votes
1answer
112 views
Does eligibility traces and epsilon-greedy do the same task in different ways?
I understand that in Reinforcement Learning algorithms such as q-learning, to prevent selecting the actions with greatest q-values too fast and allow for exploration, we use eligibility traces.
Here ...
5
votes
1answer
134 views
What makes learned feature detectors specialize in CNN?
It has been shown that it is possible to use unsupervised learning techniques to produce good feature detectors in CNNs. I can't understand what drives specialization of those feature detectors. In ...
1
vote
0answers
27 views
Word treatement with artificial intelligence
I am new to the AI topic, following on this topic very closely since one year now. Time comes to get deeper into AI and start using it on real examples.
We have several hundred employees processing ...
4
votes
3answers
4k views
Using Machine/Deep learning for guessing Pseudo Random generator
Is it possible to feed a neural network, the output from a random number generator and expect it learn the hashing/generator function. So that it can predict what will be the next generated number? ...
5
votes
2answers
985 views
What is the difference between assisted and unassisted learning in relation to AI?
Is this related to supervised and unsupervised machine learning? Is it related to AI assisted human learning, and what is the distinction?
Also, why is assisted machine learning seen as an ...
2
votes
3answers
115 views
Why do Decision Tree Learning Algorithm preferably outputs the smallest Decision Tree?
I have been following the ML course by Tom Mitchel.
The inherent assumption while using Decision Tree Learning Algo is: The algo. preferably chooses a Decision Tree which is the smallest.
Why is ...
4
votes
1answer
183 views
Unsupervised alien natural language learning
While conducting research, I recently stumbled upon the deep learning and natural language processing concepts. In this question they say that the ‘grammar induction’ is a ‘supervised learning’ mode. ...
1
vote
1answer
208 views
Neuro-evolution: Is it not Supervised Learning?
If I compare back-propagation to feed-forward neuro-modulation, the latter is unsupervised in that it requires no labeled data set.
Applying to it a genetic algorithm to refine topology and weights, ...
1
vote
2answers
67 views
Will artificial super-intelligence evolve to have selfishness inherent in biological systems?
A lot of experts have expressed concerns about evil super intelligence. While their concerns are valid, is it necessary, what are the chances or how the artificial super-intelligence will evolve to ...
3
votes
0answers
208 views
Is Cellular Neural Network (CNN) Neural Network?
I am researching Cellular Neural Network (CNN) and have already read Chua's two article (1988). In CNN, the cell is only in relation with its neighbors. So its is easy to use it for real time image ...
4
votes
1answer
183 views
What is the calcium equivalent role in neural networks
I understand that neural networks model biological neurons. Each node in the network represents a neuron cell and the connections between nodes represent the connections between cells. As in nature, ...
14
votes
1answer
662 views
What are the flaws in Jeff Hawkins's AI framework?
In 2004 Jeff Hawkins, inventor of the palm pilot, published a very interesting book called On Intelligence, in which he details a theory how the human neocortex works.
This theory is called Memory-...
2
votes
1answer
50 views
Is it possible for 'unsupervised learning' model to recognize features on unlabelled images?
Is it possible for unsupervised learning to learn about high-level, class-specific features given only unlabelled images? For example detecting human or animal faces? If so, how?
1
vote
1answer
209 views
How does unsupervised learning model learn?
Unsupervised learning does not involve target values, so basically targets are most likely the same as the inputs (in other words, involves no target values).
So how does this model learn?
1
vote
3answers
50 views
AIs' self-evaluation threshold
Is it possible that at some time in the future, AIs will be able to initiatively develop themselves, rather than passively being developed by humanity?
3
votes
1answer
255 views
Why does unsupervised pre-training help in deep learning?
What is the effectiveness of pre-training of unsupervised deep learning?
Does unsupervised deep learning actually work?
