229 votes
Accepted

Objective function, cost function, loss function: are they the same thing?

These are not very strict terms and they are highly related. However: Loss function is usually a function defined on a data point, prediction and label, and measures the penalty. For example: square ...
user avatar
  • 4,131
183 votes
Accepted

What is the difference between off-policy and on-policy learning?

First of all, there's no reason that an agent has to do the greedy action; Agents can explore or they can follow options. This is not what separates on-policy from off-policy learning. The reason ...
user avatar
  • 13.9k
57 votes

What is the difference between off-policy and on-policy learning?

First of all, what actually policy (denoted by $\pi$) means? Policy specifies an action $a$, that is taken in a state $s$ (or more precisely, $\pi$ is a probability, that an action $a$ is taken in a ...
user avatar
21 votes

What is the difference between bagging and random forest if only one explanatory variable is used?

The fundamental difference is that in Random forests, only a subset of features are selected at random out of the total and the best split feature from the subset is used to split each node in a tree, ...
user avatar
19 votes

What is the difference between policy-based, on-policy, value-based, off-policy, model-free and model-based?

Here is a quick summary on the Reinforcement Learning taxonomy: On-policy vs. Off-Policy This division is based on whether you update your $Q$ values based on actions undertaken according to your ...
user avatar
18 votes

Objective function, cost function, loss function: are they the same thing?

Quoting from section 4.3 in "Deep Learning" book by Ian Goodfellow, Yoshua Bengio, Aaron Courville (emphasis in the original): The function we want to minimize or maximize is called the ...
user avatar
18 votes
Accepted

How to train LSTM model on multiple time series data?

Make the identity of the agent one of the features, and train on all data. Probably train on a mini-batch of eg 128 agents at a time: run through the time-series from start to finish for those 128 ...
user avatar
  • 4,349
18 votes

Foundation models : Is it a new paradigm for statistics and machine learning?

Disclosure: I didn't have time to carefully read the full paper yet. From the abstract: Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of ...
user avatar
  • 117k
16 votes

What happens in the sub-areas of AI? (ML, DL)

This is just terminology, no need to think about it too much as different people classify different areas into different categories. For example a lot of statisticians would consider machine learning ...
user avatar
14 votes
Accepted

What is the difference between Sigmoid neurons and Stochastic binary neurons?

The only difference is that : The sigmoid neuron is able to output values between 0 and 1. The stochastic binary neurons only can output either a 0 or a 1 with the probability given by the sigmoid ...
user avatar
  • 255
14 votes
Accepted

What are the most popular artificial neural network algorithms for recognising the content of images?

According to Wikipedia, there are 4 main types of artificial neural network learning algorithms: supervised, unsupervised, reinforcement and deep learning. Unsupervised learning algorithms: ...
user avatar
  • 549
14 votes

Objective function, cost function, loss function: are they the same thing?

In Andrew NG's words- "Finally, the loss function was defined with respect to a single training example. It measures how well you're doing on a single training example. I'm now going to define ...
user avatar
13 votes
Accepted

What can we learn about the human brain from artificial neural networks?

As you mentioned, most neural networks are based on general simple abstractions of the brain. Not only are they lacking in mimicking characteristics like plasticity, but they do not take into account ...
user avatar
  • 3,716
13 votes

Objective function, cost function, loss function: are they the same thing?

According to Prof. Andrew Ng (see slides on page 11), Function h(X) represents your hypothesis. For fixed fitting parameters theta, it is a function of features X. I'd say this can also be called the ...
user avatar
  • 439
13 votes
Accepted

If we primarily use LSTMs over RNNs to solve the vanishing gradient problem, why can't we just use ReLUs/leaky ReLUs with RNNs instead?

I think there's some confusion here. The reason you have vanishing gradients in neural networks (with say, softmax) is wholly different from RNNs. With neural networks, you get vanishing gradients ...
user avatar
  • 13.3k
12 votes

What can we learn about the human brain from artificial neural networks?

Not much --- arguably nothing --- has so far been learnt about brain functioning from artificial neural networks. [Clarification: I wrote this answer thinking about neural networks used in machine ...
user avatar
  • 95.6k
10 votes

What is the difference between off-policy and on-policy learning?

The difference between Off-policy and On-policy methods is that with the first you do not need to follow any specific policy, your agent could even behave randomly and despite this, off-policy methods ...
user avatar
  • 240
10 votes

What is the difference between bagging and random forest if only one explanatory variable is used?

I would like to provide clarification, there is a disctinction between bagging and bagged trees. Bagging (bootstrap + aggregating) is using an ensemble of models where: each model uses a ...
user avatar
  • 215
10 votes
Accepted

Empirical results of Machine Learning/Deep Learning in practice

I don't think it would be possible to answer this question with respect to proprietary models used by private enterprise. But there is a vein of scholarship that focuses on flawed practices, such as ...
user avatar
  • 80.3k
10 votes
Accepted

Foundation models : Is it a new paradigm for statistics and machine learning?

The Bitter Lesson is that in the long term, progress is dependent on leveraging more and more computational power. This is not to say that algorithmic and modeling progress isn't important, but they ...
user avatar
  • 23.3k
9 votes

What is the difference between bagging and random forest if only one explanatory variable is used?

Bagging in general is an acronym like work that is a portmanteau of Bootstrap and aggregation. In general if you take a bunch of bootstrapped samples of your original dataset, fit models $M_1, M_2, \...
user avatar
8 votes

What can we learn about the human brain from artificial neural networks?

It is certainly not true that the human brain only uses "a few" convolutional layers. About 1/3 of the primate brain is somehow involved in processing visual information. This diagram, from Felleman ...
user avatar
  • 19.4k
8 votes

Is it still worth going into machine learning/AI?

My father went to university shortly after World War II and he used to tell me about how he once did a long Fourier transformation and how they used those very long paper rolls, as they did it in a ...
7 votes
Accepted

Why is weight initialized as 1/sqrt(# of hidden nodes) in neural networks

The whole point of that initialisation scheme (sometimes called "Xavier initialisation") is to mitigate the problem of disappearing gradients caused by the form of many activation functions. ...
user avatar
  • 2,051
7 votes

What is intuition behind high variance of Monte Carlo method?

In RL, for value functions, the bias and variance refer to behaviour of different kinds of estimate for the value function. The value function's true value is the expected return from a specific ...
user avatar
  • 6,274
6 votes

Objective function, cost function, loss function: are they the same thing?

The loss function computes the error for a single training example, while the cost function is the average of the loss functions of the entire training set.
user avatar
  • 71
5 votes

What Percent of Neural Network is used while processing a single image

That depends on the image. In general the answer is 100%, but in different strengths, depending on both the image and the specific network. In fact, encouraging full-network usage is one of the ...
user avatar
  • 11.6k
5 votes

In a neural network, do biases essentially need updates when being trained?

The idea is to learn the bias weights but have the activation fixed at 1. Anything else would make it an additional ordinary unit.
user avatar
  • 248

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