The Stack Overflow podcast is back! Listen to an interview with our new CEO.

Questions tagged [machine-learning]

Questions about computer algorithms that automatically discover patterns in data and make good decisions based on them.

Filter by
Sorted by
Tagged with
1
vote
1answer
76 views

Question on word probability for hierarchical softmax used in natural language processing

I am reading the following paper: https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf On page 4 of the paper they describe the ...
2
votes
1answer
250 views

Parameter sharing / weight constraints in Neural Networks

I would like to train a neural network whose parameters (alternatively, weights) are subject to linear constraints such as $w_{i,j} = w_{i',j'}$, where $w_{i,j}$ denotes the weight from input node $...
2
votes
1answer
76 views

Is there a universal learning rate for NeuralNetworks?

I'm currently creating a NeuralNetwork with backpropagation/gradient descent. There is this hyperparameter introduced called "learning rate" (η). Which has to be chosen to guarantee not overshooting ...
2
votes
1answer
43 views

Using a 2nd neural network to predict 1st neural network prediction error

So for example, we are trying to predict the amount of rainfall in the afternoon base on continuous features such as humidity and temperature in the morning. 1st neural network: Regression neural ...
1
vote
2answers
82 views

The well-known classifiers that can be trained/tested in linear time [closed]

I am interested in collecting the list of the classifiers that (depending on their setting) can have linear time complexity (both in training and testing step) with respect to the number of samples $n$...
1
vote
1answer
20 views

Finding a non-boundary, local optimum of a non-convex function over a convex feasible region

I have a reasonably smooth non-convex non-monotone function in high(ish) dimensional space, that I wish to find a local minimizer for, over a convex feasible region (the intersection of a ball with a ...
0
votes
0answers
67 views

Clustering non-overlapping time series

I have thousands of times series of different length and different time. I want to group them together so that I know the optimal ones to pick as input for a ML algorithm and to document how they are ...
0
votes
0answers
48 views

Adding and removing output layer units of a neural network

I'm fairly new to deep learning, so if terminology makes no sense, please let me know so I can clarify what I mean. We're working with a neural network for applying classes to inputs. That is, each ...
1
vote
0answers
92 views

Clustering via Max-Cut

I wonder if there are papers that uses max cut algorithm(s) to cluster data. For example, if an edge between two nodes $u$ and $v$ indicate that $u$ and $v$ are different, then the max-cut in some ...
0
votes
1answer
106 views

Existence of Optimal Policy for infinite-state MDPs

It is well-know from Puterman's book (1994) that in any finite-state MDP, if there exists an optimal policy, then that policy is stationary and deterministic. How about MDPs with continuous state ...
1
vote
0answers
52 views

Multi Arm Bandit (MAB) — Increasing reward function

In the general stochastic MAB model, the reward obtained at each trial is generally assumed to be independent of previous trials and obtained from some fixed (but unknown) distribution. However, if ...
1
vote
0answers
196 views

VC Dimension of A Set of Hypothesis

I am confused about what does a VC dimension of a set of hypothesis means. I have two hypothesis, say $H_1$ with VC dimension of $x$, and $H_2$ of VC dimension of $y$. Does this automatically mean ...
2
votes
1answer
138 views

Capsule networks for classification with limited data

Capsule networks seem to match performance of convolutional neural networks on image classification tasks (more specifically on classification of handwritten digits in the MNIST dataset) 1. I have ...
0
votes
1answer
38 views

Naive Bayes' Classification and Using the Entire Vocabulary in the Denominator

I am working through the NLP notes for Naive Bayes' classification here: https://web.stanford.edu/~jurafsky/slp3/6.pdf Below $c$ is the class of the observation and $w_i$ is the $i$th word of a text ...
1
vote
1answer
20 views

CNN/Neural Network: Can I still estimate 3 parameters if my input data has insufficient parameter labels?

I am trying to simplify a CNN model. Currently, I need to train 3 different models (with the same architecture) to estimate each parameter. I am just wondering if there is a way to just train one ...
2
votes
0answers
79 views

Approximate dot product between neural network output layer's parameter vector and input activations with winner-take-all hashing

In the paper Deep Networks with Large Output Spaces, Vijayanarasimhan et al. describe their approach to approximating the dot product between a neural network's output layer's parameter vector and ...
1
vote
0answers
16 views

How to use WISARD neural network to detect defects in banknotes

We learned about the WISARD neural network in my machine learning course. We said that for an $n\times k$ image, we would use discriminators having $n$ RAM neurons each of $2^k$ bits. The examples we ...
4
votes
0answers
343 views

graph signal processing

What's the intuition behind a ''Graph fourier transform'' ? I'm not so much interested in mathematical details or technical applications. I'm trying to grasp what a graph fourier transform actually ...
0
votes
0answers
35 views

Q-Learning Error Bounds

I have searched a lot for this, but apparently there is no result on calculating any bound on the error $||Q-Q^*||$ when I stop Q-learning after say $N$ iterations ($Q$ is the vector of Q-values at ...
1
vote
1answer
34 views

Does selecting the same arm has the same reward?

In multi-armed bandit problem, we have a set of $K$ arms. In each round $t$, a bandit selects an arm $k$ and receives a reward $r_{kt}$. The objective is to maximize the rewards after $T$ rounds. My ...
1
vote
0answers
32 views

How would you go about creating a algorithm that should generate a shakespearean sonnet on any given theme

I need to create an algorithm that is going to create a shakespearean sonnet for a specific theme. This theme should be generated out of twitter tweets that have some hashtag. My current idea goes ...
1
vote
0answers
25 views

Attribute Selection for minimum number of clusters

I have a table consisting of some headers $P, Q, R, S$ (shown in blue in Table 1). According to the headers, the column $T$ is populated using some predefined logic. Now, any of the headers $P,Q,R,S$ ...
2
votes
1answer
250 views

Are there connections between the theory of computation and machine learning?

I am wondering if studying the Theory of Computation/ Computational Complexity theory, specifically Sipser's 'Introduction to the Theory of Computation' will help me do machine learning/statistics/...
0
votes
0answers
290 views

How to recognize digits in water meter image

I need to read the digits of images like the one below: From what I understand, this will involve: Registering and segmenting the image into each individual digit Hand labeling a bunch of these ...
0
votes
0answers
545 views

Use Machine Learning to predict when a Gas Station is running out of fuel

We have years of data on several Gas-Stations. Data about the Gas-Stations: the number of tanks, Gallons per tank, Location, number of pumps, kind of fuel, etc. Data on fuel consumption for x gas ...
0
votes
1answer
74 views

What does canonical extension mean?

Density-reachability is a canonical extension of direct density-reachability. What is meant by canonical extension? Source: A Density-Based Algorithm for Discovering Clusters in Large Spatial ...
0
votes
2answers
456 views

What is a monotone dataset and monotone classification?

Classification algorithms, such as k-Nearest Neighbors, are well known in machine learning area, but I faced this new expression Monotone classification and I wonder what does it stand for. I guess ...
0
votes
0answers
60 views

machine learning- Hoeffding’s inequality and PAC Model

I have the following Question: A speed-dating event consists of n women and n men. An event has many rounds: In a round, each woman meets one man for 5 minutes, and decides whether to go out on a real ...
1
vote
0answers
35 views

Good pointers to learn foundations of Program induction and Program synthesis

I was interested in learning more about program induction and program synthesis. I was especially interested in learning about how to form program from data for example. My background is in ...
0
votes
1answer
95 views

Bias or not when finding patterns using data mining techniques?

I am currently following a course on Data Mining and i am very curious about the deeper underlying method. As far as i have learned so far data mining is about finding unknown patterns that can be ...
1
vote
1answer
917 views

What machine learning training algorithm to use for this kind of string dataset?

I am working on a project where I have to train the following data-set using machine learning algorithm. One of my friend suggested decision tree, but I have never seen a situation where independent ...
1
vote
0answers
167 views

Machine learning for labelling a directed graph

Just a pre-warning - I'm new to machine learning and the concepts that come with it, so please be nice with the terminology! I have a directed Graph which represents a home and some devices in it. ...
5
votes
2answers
591 views

What exactly representational bottleneck in InceptionV3 means?

I am trying to understand the concepts behind the InceptionNet V3 and got confused with the meaning of representational bottleneck. They said One should avoid bottlenecks with extreme compression. ...
0
votes
1answer
79 views

How to find max margin for non-separable SVM?

I am new to Machine Learning. Suppose a training set of positive (square) and negative (circle) points is given like: Obviously there would be no nice linear separator of positive and negative points....
0
votes
2answers
37 views

Eligibility trace and the role of gamma and lambda

From R.Sutton's book, the eligibility trace update rule is: $$ E_t(s)\leftarrow\gamma~\lambda~ E_{t-1}(s)+\mathbb{1}(S_t=s) $$ I wonder why do we need both $\gamma$ and $\lambda$ to assign credit to ...
2
votes
1answer
39 views

Decision Tree Learning Deviation - Russell and Norvig

I am working through the Russell and Norvig AI book and came across the following on the top of page 706. The section concerns Decision Tree pruning and testing a given attribute against the null ...
2
votes
1answer
41 views

Finding the maximum of a random forest

If we have some collection of decision trees with single-variable splits and a constant value at each leaf node, the average over all trees gives some function from $\mathbb{R}^n \to \mathbb{R}$. Is ...
1
vote
1answer
100 views

What machine learning algorithm to use and how to implement it?

I have a virtual world with a grid filled with squares (x by y). There are entities that can do: 1. move 1 step in the four cardinal directions 2. eat food 3. fight another entity of a different type ...
0
votes
2answers
81 views

Training a neural net without labels in Reinforcement Learning

I am trying to dig further into machine learning and I am making a program to play a game as a start. I have created a game that is based on the mobile game Flappy Bird and can be generalized to the ...
0
votes
0answers
34 views

how to add bound to clustering algorithm?

I've got a numeric matrix with 72 rows and 2 columns where the first column is the index value and the other column has sequence from 0 to 5 repeated 12 times. The dataset is like above: ...
2
votes
0answers
45 views

About gradient descent on non-convex functions

There is this "folklore" result that gradient descent on a non-convex function takes $O(\frac n {\epsilon^2})$ steps to get to a point whose gradient norm is below $\epsilon$ and with SGD this takes $...
1
vote
0answers
33 views

How do we mathematically figure out if a SVM kernel function overfits?

Looking at the kernel function (Gaussian, polynomial. chi-squared, etc) how do we figure out that changing which value will cause overfitting? In my perspective, if we increase (for example) the ...
4
votes
1answer
41 views

Do all the cells in a recurrent neural network share learned parameters?

Most descriptions of modern RNNs present a "folded" characterisation, that is to say, a single cell with a loop back to itself transmitting the hidden state from one step to the next. However, in ...
0
votes
2answers
77 views

create large data sets for machine learning

I am trying to research a new topic using machine learning. The problem is, I have a very small dataset, consisting of 5 months of data. I have been told that my dataset is too small. I want to know ...
0
votes
0answers
54 views

Naviers Stokes equation and machine learning

I am looking for a reference explaining how to solve Navier-Stokes numerically using Machine learning algorithms . Thank you in advance for your help .
1
vote
0answers
44 views

How Does a “face” tend to be defined in Face Recognition Algorithms?

So I am working on implementing YOLOv2 using my own dataset, for face detection. This requires me to prepare a training set of images annotated with the bounding box extents of faces within each image....
1
vote
0answers
10 views

Name of Generating One Value at a Time in Sequence Generation vs Encoder Decoder

a question about machine learning, specifically recurrent models: For machine translation recurrent neural networks show great promise, common here is an encoder-decoder architecture which takes a ...
1
vote
1answer
780 views

PAC learning of axis-aligned rectangles

I've been reading the proof that axis-aligned rectangles are PAC learnable from the book Foundations of Machine Learning by Mohri (Proof pt. 1, Proof pt. 2), and a small technical detail stuck out to ...
0
votes
0answers
47 views

Machine learning for recommendation systems (feed forward and recurrent neural networks)

I recently started to learn about machine learning. I have created a feed forward neural network (ffnn) and a recurrent neural network (rnn) to predict user ratings of movies. I am using a subset of ...
3
votes
1answer
350 views

CURE algorithm: what does moving the representative points towards the centroid do?

The CURE algorithm is a method of clustering data. An outline of it can be found here on slide 5: https://www.slideshare.net/ellepiu/cure-clustering-algorithm. I personally learnt it from this video: ...