Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [deep-learning]

For questions about Deep Learning (also known as deep structured learning or hierarchical learning.)

1
vote
2answers
24 views

Relative Importance of Input Features

I am confused as to how neural networks consider the different features by that have access to at the input layer. Consider this example: I have three features: an image, a dollar amount, and a ...
1
vote
0answers
18 views

Why is the learning rate is already very small (1e-05) while the model convergences too fast?

I am training a video prediction model. According to the loss plots, the model convergences very fast while the final loss is not small enough and the generation is not good. Actually, I have test ...
0
votes
0answers
12 views

Using a combination of gradient boosting with LSTM for classification? [migrated]

I am presently using a LSTM model to classify high dimensional tabular data which is not text/images (dimensions 21392x1970). I also tried XGBoost (Gradient boosting) in Python separately for the same ...
1
vote
1answer
46 views

Is it possible to use a trained neural network to predict a feature, given other features and output?

I have a neural network that is already trained to predict two continuous outputs from a set of 7 continuous features. Is there any way to apply the network to predict one of the input features, ...
1
vote
1answer
30 views

Robot Arm Deep Q Learning Actions

Hello I am new to reinforcement learning and robotics. So far I have an understanding of the concept on 2D world. You can make agent move one step in one direction. However, how do you define movement ...
0
votes
2answers
28 views

Do I need an encoder-decoder architecture to predict the next item of a sequence?

I am trying to understand how RNNs are used for sequence modelling. On a tutorial here, it mentions that if you want to translate say a sentence from English to French you can use an encoder-decoder ...
0
votes
0answers
50 views

Using AI to guess a mathematical pattern of certain polynomials in four variables: practical challenge

I'd like to use machine learning to guess a mathematical pattern: the input are certain polynomials in four variables $q_1,q_2,q_3,q_4$, the output can be zero or one. Allowed polynomials are such ...
0
votes
0answers
11 views

How do I assign a matrix of data as a label to each input image in my dataset using PyTorch? [migrated]

I want to train a convolutional neural network (CNN) in PyTorch to predict frequency spectrum data related to an input image. Rather than assigning one label to each image (Dog, Cat, Car, Airplane, ...
2
votes
2answers
46 views

Does fp32 & fp64 performance of GPU affect deep learning model training?

I am purchasing Titan RTX GPU. Everything seems fine with that except float32 & float64 performance which seems lower vis-a-vis some of its counter parts. I wanted to understand if single ...
0
votes
1answer
12 views

Should you reload the optimizer for transfer learning?

For example, you train on dataset 1 with an adaptive optimizer like Adam. Should you reload the learning schedule etc from the end of training on dataset1 when attempting transfer to dataset2? Why or ...
1
vote
0answers
17 views

How to train chat bot on infinite non-stationary data?

I have continual simulated data of million sentences of two simulated persons talking to each other in a room and I want to model one of the persons speech. Now, during this period things in the room ...
0
votes
1answer
38 views

Deep Q-learning is not performing well when there are several enemies

I am playing with a deep Q-learning algorithm in my own environment. The network can perform well as long as there is only one enemy. My agent can perform the following actions: ...
0
votes
0answers
9 views

Understanding probabilistic inference graphs

I am having trouble understanding inference graphs. In the diagram below I understand the graph on the left (forward graph) where the arrows describe the direction that data flows when training for ...
0
votes
0answers
24 views

Can a learning rate graph look unusual and weird?

I am trying to model a simple Neural Net to classify data amongst 14 classes. The data is quite high dimensional, with 21392 rows and 1970 columns, with the last column being the labels (which have ...
0
votes
1answer
47 views

How are vectors and matrices multiplied in supervised machine learning?

I've recently started reading a book about deep learning. The book is titled "Grokking Deep Learning" (by Andrew W Trask). In chapter 3 (pages 44 and 45), it talks about multiplying vectors using dot ...
0
votes
0answers
16 views

Should appending zeros to the observation space not affect deep RL algorithms?

In terms of sample complexity, is it just as easy to learn with observation space A as observation A with 10 zero's appended? For example: OpenAI Gym's fetch robotics environment has a state space ...
1
vote
0answers
30 views

Experiment shows that LSTM does worse than Random Forest… Why?

LSTM is supposed to be the right tool to capture path-dependency in time-series data. I decided to run a simple experiment (simulation) to assess the extent to which LSTM is better able to understand ...
1
vote
0answers
14 views

Multiple inputs Deep Q network Structure

An algorithmic Deep Q trader I have been working on has recently been modified to allow the passing in of multiple input states (Price, Volume, RSI) I am also looking to include further indicators ...
2
votes
1answer
33 views

Key Point Extraction the best method?

I have been researching about determining some key points on an image, in this case I'm gonna use cloth (top side of human body) pictures. I want to detect some corner points on those. Example: I ...
0
votes
0answers
4 views

How to determine the minimum scale for detectable objects in a object-detection architecture?

Note: I think the title is a bit too generic, so I'm open to suggestions on how to improve it. I'm currently working with Mask RCNN, which does instance segmentation, but I believe the question is ...
2
votes
0answers
30 views

Which Neuron represent which part of the non-linear feature?

In any neural network, each neuron in the network represents some part of non-linear feature of the input. Ex: Like in mnist data, Consider the stem of number 9 is cut into multiple pieces and ...
1
vote
0answers
12 views

Sample from a distribution inside a NN layer

Is it possible to sample from a distribution inside a neural network forward function? Assume that there is a NN and a sample is needed to be derived from it at every forward-pass to randomly set a ...
0
votes
0answers
18 views

Property graph similarity

I have N property graphs and i must calculate similarity between these graphs using deep learning. My questions are: How can i represent these graphs for deep learning or something like feature ...
0
votes
1answer
62 views

Difference between Machine learning and Deep learning? [duplicate]

What is machine learning and deep learning? I hope there are similar questions out there. But I couldn't able visualize. Can someone explain me the difference between Machine learning and Deep ...
0
votes
0answers
24 views

Contractive auto-encoders

I am trying to implement Contractive auto-encoders in PyTorch but I don't know what I'm doing is right or not. The architecture of the auto-encoder is given below: ...
0
votes
1answer
48 views

Which field to study to learn & create a.i generated simulations?

I wasn't sure how to title this question so pardon me please. You may have seen at least one video of those "INSANE A.I created simulation of {X} doing {Y & Z} like the following ones: A.I ...
0
votes
0answers
17 views

How to prevent instabilities when training a deep convolutional generative adversarial network (DC-GAN)?

I am training a deep convolutional generative adversarial network (DC-GAN) (Original Paper: 1) using PyTorch on an image dataset for a research project. Despite which category of images I attempt to ...
0
votes
0answers
7 views

How to use SLAM on other sensor other than camera?

I have a sensor that reads electromagnetic field strength from each position. And the field is stable and unique for each position. So the reading is simply a function of the position like this: <...
-1
votes
0answers
22 views

Can I pair Titan XP w/ RTX 2080 Ti?

I am looking to buy another GPU for my deep learning rig. I currently have a Titan XP but would like to be able to train models faster. I would add a second Titan XP but they have been out of stock ...
2
votes
1answer
28 views

Will LMS always be convex function? If yes, then why do we change it for neural networks?

In LMS(least mean square) since, we use a quadratic error function, and quadratic functions are generally parabola in (some convex like shape). I wonder whether that is the reason why we use least ...
2
votes
2answers
70 views

Each training run for DDQN agent takes 2 days, and still ends up with -13 avg score, but OpenAi baseline DQN needs only an hour to converge to +18?

Status: For a few weeks now, I have been working on a Double DQN agent for the PongDeterministic-v4 environment, which you can find here. A single training run ...
-1
votes
0answers
22 views

How many gradient descent iterations does it take for a neural network to over-fit, relative to network “complexity”

Following this question, I have a more refined, general, and probably more answerable question: Assuming: Infinite training data A learning problem whose loss function has no local minima (for ...
3
votes
2answers
70 views

Are neural networks statistical models?

By reading the abstract of Neural Networks and Statistical Models paper it would seem that ANNs are statistical models. In contrast Machine Learning is not just glorified Statistics. I am looking ...
0
votes
0answers
10 views

How to remove unwanted signals from the sensor measurement?

I have 2 tabular datasets, one is clean and one is drifted. They are records of sensor measurements. I move the sensor around in the room and collected thousands of measurements. I have a sensor that ...
2
votes
1answer
46 views

Sun loving social AI spider robot?

Platonic solids are regular, convex, and equilateral polyhedrons with congruent faces and a congruent number of edges meeting at the vertices. We can see them in toys; the six faces of the cube ...
-2
votes
1answer
101 views

What is the difference between Deep learning and Machine learning? [duplicate]

I'm confused about these two, Is there any difference between them? and how can I learn more about them?
3
votes
1answer
29 views

How to identify too small network in reinforcement learning?

I am using Open AI's code to do a RL task on an environment that I built myself. I tried some network architectures, and they all converge, faster or slower on CartPole. On my environment, the ...
1
vote
2answers
30 views

Approach to classify a photo and extract text from it

I am trying to make a personal ML project where my objective is using a photo from an invoice, for instance, a Walmart invoice, classify it as being a Walmart invoice and extract the total amount ...
1
vote
1answer
56 views

DQN stuck at suboptimal policy in Atari Pong task

I am in the process of implementing the DQN model from scratch in PyTorch with the target environment of Atari Pong. After a while of tweaking hyper-parameters, I cannot seem to get the model to ...
1
vote
0answers
22 views

Deep Learning on how to find out the body measurement (e.g. shoulder length, waist, hips, legs length etc) from mobile camera captured images?

I do understand that there are plenty of mobile apps available for body measurement (e.g. MTailor) or creating 3D model (3dlook). What I would like to find out is how we can use deep learning to ...
2
votes
0answers
15 views

Training, test, dev split in speech recognition

Unfortunately there is no speech-recognition or speech-to-text tag yet so I go with the ...
6
votes
3answers
131 views

How can a neural network learn when the derivative of the activation function is 0?

Imagine that I have an artificial neural network with a single hidden layer and that I am using ReLU as my activating function. If by change I initialize my bias and my weights in such a form that: $$ ...
0
votes
1answer
47 views

Meta-learning vs Zero-shot learning

My question is whether Meta-learning and Zero-shot learning are synonymous? I have seen articles where they seem to imply that they are at least very similar concepts.
0
votes
1answer
56 views

BERT - What are the segment and position embeddings used in here?

They only reference in the paper that the position embeddings are learned, which is different from what was done in ELMo. ELMo paper - https://arxiv.org/pdf/1802.05365.pdf BERT paper - https://arxiv....
-2
votes
0answers
46 views

Prediction model as helper for a DQN agent

Suppose I have a regression model that can make predictions on stock price movements for 10 steps ahead. The labels are ...
-1
votes
1answer
47 views

What will Q-values look like in self-play tic-tac-toe?

This corresponds to Exercise 1.1 of RLBook, and a discussion followed from here. Considering two reward schemes- Win = +1, Draw = 0, Loss = -1 Win = +1, Draw or Loss = 0 Can we say something about ...
0
votes
1answer
42 views

What's the commercial usage of “image captioning”?

If "image captioning" is utilized to make a commercial product, what application fields will need this technique? And what is the level of required performance for this technique to be usable?
2
votes
2answers
48 views

How do I combine two electromagnetic readings to predict the position of a sensor?

I have an electromagnetic sensor and electromagnetic field emitter. The sensor will read power from the emitter. I want to predict the position of the sensor using the reading. Let me simplify the ...
1
vote
0answers
22 views

How does the norm of a weight matrix changes during training?

I have a neural network $F(W,x): \mathbb{R}^d \rightarrow \mathbb{R}^k$ with $L$ layers, $m$ neurones per layer, ReLu activation, softmax on the last layer and $n$ datapoint. My loss function is the ...
2
votes
1answer
82 views

Additive Attention in Convolutional Networks

Attention has been used widely in recurrent networks to weight feature representations learned by the model. This is not a trivial task since recurrent networks have a hidden state that captures ...