All Questions

Filter by
Sorted by
Tagged with
0
votes
0answers
5 views

Faster RCNN-RPN Network Training

I am trying to understand RPN network in Faster RCNN. I understand the concept of RPN network, Pass the input images to the pre trained CNN, and get the output as feature maps Make fixed size of the ...
0
votes
0answers
16 views

Best way to extract varied size rectangle from video

I am trying to apply a CNN model for each video frame, except that my input videos are video calls, which contain many windows like this example and model is trained on a single person's call. So, ...
0
votes
0answers
6 views

In what conditions can we claim that we are using Auto ML?

From previous question, Nbro said Automated machine learning (AutoML) is an umbrella term that encompasses a collection of techniques (such as hyper-parameter optimization or automated feature ...
1
vote
0answers
19 views

Doing backpropagation in an Tensorflow.js Neural Network

I have a neural network (which I am making from scratch). In order to make the neural network "learn" I need to conduct back-propagation. Using the code at the below how would I conduct back-...
0
votes
0answers
11 views

Time Series Forecasting - Recurrent Neural Networks (tensorflow)

I am attempting to forecast a time series using tensorflow with the following code: ...
2
votes
1answer
61 views

What is the scope of real-world deep learning applications in 2020?

2015 was a milestone year for AI--"deep learning" was validated in a very public way with AlphaGo. However, at the time, the question was raised: "What else is deep learning good for?&...
0
votes
0answers
14 views

real time updating of computer vision classes

Suppose you have a ground plane and can use a stereo vision system to detect things which are possibly separate objects. Suppose also your robot or agent can attempt to pickup and move these objects ...
0
votes
1answer
25 views

What is the most appropriate ML algorithm for creating recommendations

I am trying to find the best algorithm to create a list of recommendations for a user based on the interests of all other users. Say I have a list of of samples: ...
1
vote
1answer
32 views

Is value iteration stopped after one update of each state?

In section 4.4 Value Iteration, the authors write One important special case is when policy evaluation is stopped after just one sweep (one update of each state). This algorithm is called value ...
0
votes
0answers
8 views

Neural network architecture for DDPG agent in Matlab - standard networks?

I want to dive into Reinforcement Learning and therefore as a little project I am trying to swing up and balance a Furuta pendulum in Simulink. Unfortunately I don´t really know where to start, when ...
0
votes
0answers
10 views

Transfer Learning: Finetune a model with a splitted dataset?

Lets say I want to fine-tune a model. I have a pretrained ResNet model and on top of this model I add some extra layers. And lets say I have a dataset of 10,000 images. The recommended way would be: ...
0
votes
0answers
13 views

How to find lowest value value of ordering

I have data containing 50 lines like this: ...
0
votes
0answers
14 views

How to compute the target for double Q-learning update step?

I've already read the original paper about double DQN but I do not find a clear and practical explanation of how the target $y$ is computed, so here's how I interpreted the method (let's say I have 3 ...
1
vote
1answer
19 views

Finding the optimal policy from a set of fixed policies in reinforcement learning

This is an open-ended question.Suppose I have a reinforcement learning task that is being solved using many different fixed policies, one of which is optimal. The goal of the agent is not to figure ...
4
votes
1answer
41 views

Why are policy iteration and value iteration studied as separate algorithms?

In Sutton and Barto's book about reinforcement learning, policy iteration and value iterations are presented as separate/different algorithms. This is very confusing because policy iteration includes ...
3
votes
0answers
25 views

What does the number of required expert demonstrations in Imitation Learning depend on?

I just read the following points about the number of required expert demonstrations in imitation learning, and I'd like some clarifications. For the purpose of context, I'll be using a linear reward ...
1
vote
1answer
41 views

What is the surrogate loss function in imitation learning, and how is it different from the true cost?

I've been reading A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning lately, and I can't understand what they mean by the surrogate loss function. Some relevant ...
2
votes
1answer
21 views

What are the pros and cons of sparse and dense rewards in reinforcement learning?

From what I understand, if the rewards are sparse the agent will have to explore more to get rewards and learn the optimal policy, whereas if the rewards are dense in time, the agent is quickly guided ...
0
votes
0answers
18 views

Customized food for persons based on their profile using Reinforcement learning

I am newbie to Reinforcement Learning, this is my idea - Agent(food provider) has to select a food based on the environment(based on the user profile). Here the reward will be given to the agent based ...
1
vote
1answer
27 views

In DQN, when do the parameters in the Neural Network update based on the reward received?

I'm aware that we back-propagate after computing the loss between: The Neural Network Q values and the Target Network Q values However, all this is doing is updating the parameters of the Neural ...
0
votes
0answers
30 views

Is there a continuous version of clustering?

Is there a continuous version of clustering? i.e. detecting N peaks on a plane.
1
vote
1answer
26 views

Why are Target Networks used in Deep Q-Learning as opposed to the Expected Value equation?

I understand we use a target network because it helps resolve issues regarding stability, however, that's not what I'm here to ask. What I would like to understand is why a target network is used as a ...
0
votes
0answers
9 views

What is the best NLP model for handeling a rapid extension of the production data for a question answeing task

I'm lately writing a chat-bot to answer questions about children's fantasy books I save to my database . When a user opens a book it loads the chat-bot for the given book . I don't need it to work on ...
0
votes
1answer
24 views

What is Precision@K for link prediction in graph embedding meaning?

I am trying to re-implement the SDNE algorithm for graph embedding by PyTorch. I get stuck at some issues about evaluation metric Precision@K. precision@k is a metric which gives equal weight to the ...
0
votes
0answers
10 views

DQN in non-episodic tasks?

Are there any reference papers that DQN-like methods are used in continuous, non-episodic tasks?
1
vote
1answer
29 views

Do all filters of the same convolutional layer need to have the same dimensions and stride?

In Convolutional Neural Networks, do all filters of the same convolutional layer need to have the same dimensions and stride? If they don't, then it would seem the channel produced by each filter ...
1
vote
1answer
42 views

When using experience replay in reinforcement learning, which state is used for training?

I'm slightly confused about the experience replay process. I understand why we use batch processing in reinforcement learning, and from my understanding, a batch of states is input into the neural ...
8
votes
2answers
941 views

Why is depth-first search an artificial intelligence algorithm?

I'm new to the artificial intelligence field. In our first chapters, there is one topic called "problem-solving by searching". After searching for it on the internet, I found the depth-first ...
0
votes
0answers
10 views

Why does the RNN-T beam search algorithm need to loop over the prefixes of y

I'm looking at the beam search psuedo code for the RNN-T decoder https://arxiv.org/pdf/1211.3711.pdf Why are lines 5-7 needed?
0
votes
0answers
23 views

My Deep Q-Learning Network does not learn for OpenAI gym's cartpole problem

I am implementing OpenAI gym's cartpole problem using Deep Q-Learning (DQN). I followed tutorials (video and otherwise) and learned all about it. I implemented a code for myself and I thought it ...
1
vote
1answer
41 views

Implementing Gradient Descent Algorithm in Python, bit confused regarding equations

I'm following the guide as outlined at this link: http://neuralnetworksanddeeplearning.com/chap2.html For the purposes of this question, I've written a basic network 2 hidden layers, one with 2 ...
0
votes
0answers
26 views

What is the purpose to have fully connected layers?

What is the purpose of a fully connected multi layer perceptron in which every input is connected to every output by a weight? After all, the information is only distributed over several channels, but ...
0
votes
0answers
9 views

Python code in LSTM to look at selective history

My dataset has 3 columns - a,b,c. Using b (and its history), I wish to predict c. Using list function and converting to array, I can tell python to look at last 20 b's for any b, as input to predict c....
0
votes
0answers
26 views

What are the most used and effective activation functions for sentiment classification with an recurrent neural network?

I am making an RNN for sentiment classification. What activation functions would you use in order to achieve this goal (excluding the one present in the output layer)?
0
votes
0answers
11 views

What is the current way robots can assess and traverse difficult obstacles in 3d space?

What is the current way robots can assess and traverse difficult obstacles in 3d space? I could see manual feature extraction using stereo vision (for example, the height of the obstacle, "...
2
votes
0answers
25 views

How do RNN's for sentiment classification deal with different sentence lengths?

I have been doing a course which teaches you about Deep Neural Networks, during one of the exercises I was made to make an RNN for sentiment classification which I did, but I did not understand how an ...
1
vote
1answer
33 views

What is the representational capacity of a learning algorithm? [duplicate]

The definition I see for representational capacity is "the family of functions the learning algorithm can choose from when varying the parameters in order to reduce a training objective." (...
0
votes
0answers
8 views

how to encode categorial input with group-subgroup information for neural networks

I am a newbie for this area of research, and just started getting my hands wet testing some ideas. One problem I have is my data has a column that is a categorical input selected from about 1,000 ...
1
vote
0answers
29 views

What is the time complexity of the upsampling stage of the U-net?

I am trying to determine the complexity of the neural network we use. The neural network is a U-net generator with an input shape of NxN (not an image but image-like data) and output of the same shape....
0
votes
0answers
23 views

Select training data for episodic reinforcement learning (stock trading agent)

I playing around with a stock trading agent trained via (deep) reinforcement learning, including memory replay. The agent is trained for 1000 episodes, where each episodes consists of 180 timesteps (e....
1
vote
0answers
19 views

Trying to proof off policy TD Learning formula

I was reading the book "Introduction to Reinforcement Learning" by Richard Sutton In section 7.3 he write the formula for n-step off-policy TD as:. $$V(S_t) = V(S_{t-1}) + \alpha \rho_{t:t+n-...
1
vote
1answer
27 views

What is layer freezing in transfer learning?

Transfer learning consists of taking features learned on one problem and leveraging them on a new, similar problem. In the Transfer Learning, we take layers from a previously trained model and freeze ...
2
votes
0answers
49 views

Should I use the discounted average reward as objective in a finite-horizon problem?

I am new to reinforcement learning, but, for a finite horizon application problem, I am considering using the average reward instead of the sum of rewards as the objective. Specifically, there are a ...
0
votes
0answers
10 views

How does YOLO handle non-class objects?

I have been reading more about computer vision and I'm bothered by YOLO and similar deep learning architectures. The thing I am confused on is how non-class image sections are dealt with, in ...
4
votes
2answers
88 views

How can we prevent AGI from doing drugs?

I recently read some introductions to AI alignment, AIXI and decision theory things. As far as I understood, one of the main problems in AI alignment is how to define a utility function well, not ...
1
vote
1answer
28 views

How can Transformer Networks handle arbitrary length input

Transformer Networks, introduced in this paper is a popular new NLP architecture that is commonly viewed as an alternative to Recurrent Architectures like LSTMs and GRUs. However, having gone through ...
1
vote
0answers
10 views

Is there a problem for “Sound Source Identification in Video Footage”?

I've been considering starting a project for some time on sound source identification. To be more specific, my goal is to be able to identify the "sources" for sound in videos. Moving parts ...
1
vote
1answer
27 views

What is the Preferred Mathematical Representation for a Forward Pass in a Neural Network?

I know this may be a question of semantics but I always see different articles explain forward pass slightly different. e.g. Sometimes they represent a forward pass to a hidden layer in a standard ...
0
votes
0answers
24 views

Where can I find short videos of examples of RL being used?

I would like to add a short ~1-3 minute video to a presentation, to demonstrate how Reinforcement Learning is used to solve problems. I am thinking something like a short gif of an agent playing an ...

15 30 50 per page
1
2 3 4 5
145