Questions tagged [implementation]

For questions about implementation of software/algorithms related to Artificial Intelligence.

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

Why is the logarithm of the standard deviation used in this implementation of proximal policy optimization?

I am currently writing my bachelor thesis, which is an implementation of proximal policy optimization. Sometimes, I hit a wall because of the gaps in my mathematical knowledge. However, implementing ...
4
votes
2answers
100 views

How is the AI in 3d games implemented?

A few days ago, I started looking a bit more into AI and learning about the way it works, and it is very interesting, but I can't find a clear answer on how the artificial intelligence is implemented ...
0
votes
1answer
25 views

What to do with a GAN that trained well but got worse over time?

I am training a WGAN-GP network based on the following paper, though I am using a different dataset. Now, for the first ~ 60-70 epochs, my network trained really well, which I could see in the loss ...
1
vote
1answer
105 views

Is there a convention on the order of multiplication of the weights with the inputs in neural nets?

Is there a convention on how the input data and the weights are multiplied? The input data can be anything, including the result from the previous layers. There are two options: Option 1: $$\begin{...
4
votes
1answer
59 views

How should I implement the state transition when it is a Gaussian distribution?

I am reading this paper Anxiety, Avoidance and Sequential Evaluation and is confused about the implementation of a specific lab study. Namely, the authors model what is called the Balloon task using a ...
0
votes
0answers
23 views

Is the dimensionality of the query and key tensors in this implementation of the transformer's self-attention correct?

Looking at this tutorial matmul_qk = tf.matmul(q, k, transpose_b=True) # (..., seq_len_q, seq_len_k) is the output of two tensors multiplied of shape: ...
1
vote
0answers
52 views
1
vote
1answer
50 views

How do you pass the image from one convolutional layer to another in a CNN?

I am currently trying to write a CNN from scratch, but I don't understand how to feed the information from a max-pooling layer to the next convolutional layer. Specifically, I don't know what to do ...
5
votes
0answers
64 views

Wasserstein GAN: Implemention of Critic Loss Correct?

The WGAN paper concretely proposes Algorithm 1 (cf. page 8). Now, they also state what their loss for the critic and the generator is. When implementing the critic loss (so lines 5 and 6 of Algorithm ...
1
vote
0answers
16 views

Would it make sense to share the layers (except the last one) of the neural networks in Double DQN?

Context: Double Q-learning was introduced to prevent the maximization bias from q-learning. Instead of learning a single Q-network, we can learn two (or in general $K > 1$) and our Q-estimate would ...
2
votes
1answer
70 views

How are continuous actions sampled (or generated) from the policy network in PPO?

I am trying to understand and reproduce the Proximal Policy Optimization (PPO) algorithm in detail. One thing that I find missing in the paper introducing the algorithm is how exactly actions $a_t$ ...
1
vote
1answer
29 views

Is average pooling equivalent to a strided convolution with a specific constant kernel?

It seems to me that average pooling can be replaced by a strided convolution with a constant kernel. For instance, a 3x3 pooling would be equivalent to a strided convolution (of stride $3$) with a $3 \...
1
vote
0answers
41 views

How am I supposed to code equation 4.57 from the book “Machine Learning: An Algorithmic Perspective”?

Consider the equation 4.57 (p. 108) from section 4.6 of the Book Machine Learning: An Algorithmic Perspective, where the derivative of the softmax function is explained $$\delta_o(\kappa) = (y_\kappa -...
1
vote
0answers
31 views

What is the difference between step_model and train_model in the OpenAI implementation of the A2C algorithm?

I'm struggling a little with understanding the OpenAI implementation of A2C in the baselines (version 2.9.0) package. From my understanding, one ...
1
vote
2answers
308 views

What are some alternatives to “Papers with Code”?

There are lots of research papers available that are worth reading. We can read papers easily, but the associated code (not necessarily the official one developed by the authors of the paper) is often ...
1
vote
1answer
69 views

What are the variables that need to be saved and loaded, so that a DQN model starts where it left off?

TensorFlow allows users to save the weights and the model architecture, however, that will be insufficient unless the values of certain other variables are also stored. For instance, in DQN, if $\...
3
votes
1answer
47 views

How can I create an embedding layer to convert words to a vector space from scratch?

For an upcoming project, I am trying to build a neural network for classifying text from scratch, without the use of libraries. This requires an embedding layer, or a way to convert words to some ...
1
vote
0answers
24 views

What is the score used to visualize attention in this paper?

I'm reading this paper Global-Locally Self-Attentive Dialogue State Tracker and follow through the implementation published in GLAD. I was wondering if someone can clarify what variable or score is ...
1
vote
1answer
217 views

What is a RAM state in the gym's breakout-ram environment?

I have encountered the gym environment and decided to create AI that plays breakout. Here is the link: https://gym.openai.com/envs/Breakout-ram-v0/. The documentation says that the state is ...
1
vote
1answer
56 views

Is there a general file type associated with AI projects?

This is a general question. Is there a general file type associated with AI projects? Photoshop = .psd Excel = csv Artificial Intelligence = ?
2
votes
1answer
210 views

What made your DDPG implementation on your environment work?

I am working on scheduling problem that has inherent randomness. The dimensions of action and state spaces are 1 and 5 respectively. I am using DDPG, but it seems extremely unstable, and so far it ...
1
vote
1answer
45 views

Is there a good and easy paper to code policy gradient algorithms (REINFORCE) from scratch?

I am interested in learning about policy gradient algorithms and REINFORCE. Can you suggest a good and easy paper that I can use to code them from scratch?
2
votes
1answer
51 views

How can I implement policy evaluation when reward is tied to an action outcome?

I'm following Stanford reinforcement learning videos on youtube. One of the assignments asks to write code for policy evaluation for Gym's FrozenLake-v0 environment. In the course (and books I have ...
3
votes
3answers
182 views

Why can the Bellman equation be turned into an update rule?

In chapter 4.1 of Sutton's book, the Bellman equation is turned into an update rule by simply changing the indices of it. How is it mathematically justified? I didn't quite get the initiation of why ...
3
votes
0answers
519 views

How much time does it take to train DQN on Atari environment?

I am trying to build a DQN model for the Atari Pong game, but I am not sure whether the model is learning at all. I am using the architecture described in the paper Playing Atari with Deep ...
2
votes
0answers
40 views

How can I get to a final output of shape $224 \times 224$, without FC layers, from a tensor of specific shape, in OpenPose?

I am approaching the implementation of the OpenPose algorithm for realtime human body pose estimation. According to the official paper OpenPose: Realtime Multi-Person 2D Pose Estimation using Part ...
1
vote
1answer
86 views

Why isn't the implementation of my policy evaluation for a simple MDP converging?

I am trying to code out a policy evaluation algorithm to find the $V^\pi(s)$ for all states. The following diagram below shows the MDP. In this case i let p = q = 0.5. the rewards for each states ...
2
votes
0answers
431 views

How can I implement derivative of softmax function for matrices in Python? [closed]

I have trouble understanding how to implement derivative of softmax function. Here is what I tried: ...
3
votes
1answer
98 views

How difficult is this sound classification?

I want a microphone to pick up sounds around me (let's say beyond a 3 foot radius), but ignore sounds made at my desk, such as the rustling of paper, clicking a mouse and typing, my hands brushing up ...
1
vote
0answers
56 views

Why are the current means and the old ones the same in this implementation of Elastic Weight Consolidation?

I'm trying to re-implement Elastic Weight Consolidation (EWC) as outlined in this paper. As a reference, I am also using this Github repository (another implementation). My model/idea is pretty ...
2
votes
1answer
70 views

From an implementation point of view, what are the main differences between an RNN and a CNN?

I understand that in general an RNN is good for time series data and a CNN image data, and have noticed many blogs explaining the fundamental differences in the models. As a beginner in machine ...
2
votes
0answers
141 views

Are there any general tips for troubleshooting a VAE when apparently it is not learning?

I am trying to train a VAE for anomaly detection. I chose one architecture from this Github repository and I adjusted the input and output to match what I need. In my case, the input (and hence the ...
5
votes
1answer
158 views

Context-based gap-fill face posture-mapper GAN

These images are handmade, not auto-generated like they will be in production. Apologies for inaccuracies in the graph overlay. I am trying to build an AI like that displayed in the diagram: when ...
13
votes
4answers
7k views

What does AI software look like, and how is it different from other software?

What does AI software look like? What is the major difference between AI software and other software?
3
votes
0answers
124 views

How can I increase the speed and performance of my implementation of an AI for Reversi?

I made an AI for Reversi, aka Othello (8×8), like Alpha Zero, using this book. This book is written in Japanese. The source code of the AI I implemented can be found in this Github repository. There ...
3
votes
0answers
188 views

How is the rollout from the MCTS implemented in both of the AlphaGo Zero and the AlphaZero algorithms?

In a vanilla Monte Carlo tree search (MCTS) implementation, the rollout is usually implemented following a uniform random policy, that is, it takes random actions until the game is finished and only ...
2
votes
0answers
62 views

Implementation of SVM - theory to practice

I'm studying Support Vector Machines in the machine learning course, I'm a computer scientist, I've quite understood how SVM are designed thanks also to 16. Learning: Support Vector Machines - MIT. ...
3
votes
0answers
178 views

Understanding log probabilities of actions in the PPO objective

I'm trying to implement the Proximal Policy Optimization (PPO) algorithm (code here), but I am confused about certain concepts. What is the correct way to implement log probability of a policy (...
3
votes
2answers
104 views

Are feature maps merged or are they passed on as they are?

I am unsure about the following parts of the architecture and mechanics of convolution layers in CNNs. Possibly, this is implementation-dependent though. First question: Say I have 2 convolution ...
3
votes
1answer
125 views

How does Monte Carlo Tree Search UCT exploitation value change based on perspective?

In this blog toward the end, the author writes the following: For the sake of my question, let’s assume that a terminal state gives a reward of +1 for a win and -1 for a loss. When the author says “...
4
votes
2answers
197 views

How is parallelism implemented in RL algorithms like PPO?

There are multiple ways to implement parallelism in reinforcement learning. One is to use parallel workers running in their own environments to collect data in parallel, instead of using replay memory ...
1
vote
1answer
614 views

How should I implement the backward pass through a flatten layer of a CNN?

I am making a NN library without any other external NN library, so I am implementing all layers, including the flatten layer, and algorithms (forward and backward pass) from scratch. I know the ...
4
votes
1answer
678 views

How can the convolution operation be implemented as a matrix multiplication?

How can the convolution operation used by CNNs be implemented as a matrix-vector multiplication? We often think of the convolution operation in CNNs as a kernel that slides across the input. However, ...
0
votes
0answers
89 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
1answer
453 views

Why is this PyTorch implementation of the actor-critic algorithm inconsistent with the mathematical formulas?

This PyTorch implementation of the actor-critic algorithm calculates the losses like so: ...
3
votes
1answer
2k views

How to deal with the terminal state in SARSA in a multi-agent setting?

I'm training a SARSA agent to update a Q function, but I'm confused about how you handle the final state. In this case, when the game ends and there is no $S'$. For example, the agent performed an ...
2
votes
1answer
2k views

Why do we use a last-in-first-out queue in depth-first search?

Why do we use a last-in-first-out (LIFO) queue in the depth-first search algorithm? In the breadth-first search algorithm, we use a first-in-first-out (FIFO) queue, so I am confused.
2
votes
2answers
91 views

Which of these two numerical methods for z-score normalisation is preferable, in multivariate linear regression?

In the exercise Exercise 3: Multivariate Linear Regression, by Andrew Ng, the author suggests to "scale both types of inputs by their standard deviations and set their means to zero". $$x_{n e w}=\...
5
votes
2answers
5k views

How fast is TensorFlow compared to self written neural nets? [closed]

I made my first neural net in C++ without any libraries. It was a net to recognize numbers from the MNIST dataset. In a 784 - 784 - 10 net with sigmoid function and 5 epochs with every 60000 samples, ...
3
votes
1answer
222 views

Does depth-first search always stop when it has found the leftmost solution?

I'm a fresh learner of AI. I was told that depth-first search is not an optimal searching algorithm since "it finds the 'leftmost' solution, regardless of depth or cost". Therefore, does it mean that ...