Self-Learner - Badge - Artificial Intelligence Stack Exchange

Self-Learner

Answer your own question with score of 3 or more.

Awarded 50 times.

Why does the average-reward estimator for continuing tasks use the TD error?

Awarded Oct 10 at 16:18

kmf

1067 bronze badges

Should minimax with alpha beta pruning depth be an odd number?

Awarded Oct 2 at 13:56

Carmellose

1718 bronze badges

Historical source for a saying about moving the goalposts regarding AI

Awarded Aug 4 at 21:32

Igor F.

2016 bronze badges

What is the loss function and training task on which the original BERT model was trained

Awarded Aug 4 at 16:40

Ggjj11

1781 silver badge8 bronze badges

Does BERT freeze the entire model body when it does fine-tuning?

Awarded Aug 1 at 18:42

Joon

511 silver badge6 bronze badges

What can GPT-4 do linguistics-wise?

Awarded Jul 9 at 9:07

Anixx

32110 bronze badges

Can ELMO embeddings be used to find the n most similar sentences?

Awarded Jun 11 at 15:48

brokentransform

614 bronze badges

"Attention is all you need" paper : How are the Q, K, V values calculated?

Awarded May 11 at 1:41

Soltius

2211 silver badge9 bronze badges

How does the (decoder-only) transformer architecture work?

Awarded Apr 28 at 15:27

Robin van Hoorn

2,1031 gold badge7 silver badges33 bronze badges

In variational autoencoders, why do people use MSE for the loss?

Awarded Apr 23 at 12:11

IttayD

2092 silver badges5 bronze badges

How much of the ChatGPT output is copied from its training set (vs. being abstractively generated)?

Awarded Apr 1 at 4:42

Franck Dernoncourt

2,8141 gold badge19 silver badges32 bronze badges

What's the relationship between Bayesian RL and POMDPs?

Awarded Dec 19, 2022 at 0:16

mdc

3801 silver badge12 bronze badges

What is the most important predecessor of the transformer model?

Awarded Dec 15, 2022 at 23:36

Mariusmarten

4131 silver badge16 bronze badges

How does ChatGPT retain the context of previous questions?

Awarded Dec 12, 2022 at 19:46

milez

9511 gold badge6 silver badges10 bronze badges

What, exactly, do mlp(64,64) and mlp(64,128,1024) mean in PointNet, and how many input neurons does 1 (x,y,z) point have?

Awarded Dec 2, 2022 at 22:57

Justin

416 bronze badges

A comprehensive list of machine learning algorithms

Awarded Dec 1, 2022 at 12:48

Bernardo Costa

2213 silver badges8 bronze badges

If the point of the ResNet skip connection is to let the main path learn the residual relative to identity, why are there convolutional skips?

Awarded Nov 28, 2022 at 0:41

Alexander Soare

1,3192 gold badges11 silver badges26 bronze badges

Entropy term in Proximal Policy Optimization (PPO) becomes undefined after few training epochs

Awarded Oct 27, 2022 at 20:51

Chintan Trivedi

1913 bronze badges

How to make minimax optimal?

Awarded Jun 13, 2022 at 19:35

Aadit M Shah

641 silver badge10 bronze badges

OpenAI Gym: Multiple actions in one step

Awarded Feb 23, 2022 at 11:56

stefanbschneider

1831 silver badge11 bronze badges

What kind of word embedding is used in the original transformer?

Awarded Jan 7, 2022 at 18:25

Bert Gayus

5551 gold badge3 silver badges12 bronze badges

How to embed/deploy an arbitrary machine learning model on microcontrollers?

Awarded May 6, 2021 at 16:01

Hattori

2011 silver badge7 bronze badges

What is the cost function of a transformer?

Awarded Apr 19, 2021 at 12:57

user3667125

1,5106 silver badges13 bronze badges

How do I convert an MDP with the reward function in the form $R(s,a,s')$ to and an MDP with a reward function in the form $R(s,a)$?

Awarded Mar 19, 2021 at 10:17

Asher

4363 silver badges9 bronze badges

(post deleted or otherwise unavailable)

Awarded Mar 18, 2021 at 20:49

Douglas Daseeco

7,4431 gold badge26 silver badges62 bronze badges

GAN Generator Output w/ Periodic Noise

Awarded Feb 20, 2021 at 16:32

Hazar

317 bronze badges

My DQN is stuck and can't see where the problem is

Awarded Nov 26, 2020 at 18:55

JCP

17312 bronze badges

Why we don't use importance sampling in tabular Q-Learning?

Awarded Nov 15, 2020 at 18:41

David

4,6651 gold badge7 silver badges27 bronze badges

Why is the denominator ignored in the Bayes' rule?

Awarded Oct 4, 2020 at 19:17

gcorso

3561 silver badge7 bronze badges

How can active learning be used in the case of complex models that require a lot of data?

Awarded Apr 18, 2020 at 14:26

OmG

1,75110 silver badges19 bronze badges

Do all expert trajectories have the same starting state in apprenticeship learning?

Awarded Apr 3, 2020 at 15:05

calveeen

1,2517 silver badges18 bronze badges

Is it common in RL research with Atari/ALE to automatically press FIRE to start games?

Awarded Mar 29, 2020 at 8:35

Dennis Soemers♦

10.1k2 gold badges25 silver badges67 bronze badges

Why is Standard Deviation based on L2 Variance and not L1 Variance

Awarded Feb 5, 2020 at 5:25

Dan D.

1,2831 gold badge11 silver badges35 bronze badges

What is the difference between ConvLSTM and CNN LSTM?

Awarded Nov 27, 2019 at 21:55

user239457

1811 silver badge6 bronze badges

Is there any research on the development of attacks against artificial intelligence systems?

Awarded Oct 31, 2019 at 0:35

Lion Lai

4234 silver badges9 bronze badges

Why is my implementation of Q-learning not converging to the right values in the FrozenLake environment?

Awarded Oct 15, 2019 at 19:05

abkds

1911 silver badge6 bronze badges

When will the number of neurons in AI systems equal the human brain?

Awarded Sep 25, 2019 at 19:15

Tom Hale

3643 silver badges11 bronze badges

Can LSTM neural networks be sped up by a GPU?

Awarded Aug 9, 2019 at 11:05

Dieshe

2791 gold badge2 silver badges6 bronze badges

How can the $\lambda$-return be defined recursively?

Awarded Apr 14, 2019 at 11:20

Philip Raeisghasem

2,0389 silver badges30 bronze badges

Is there an alternative to the use of target network?

Awarded Apr 10, 2019 at 15:35

Phizaz

5103 silver badges13 bronze badges

Biological analogy for boosting and inhibition idea in Hierarchical Temporal Memory (HTM)

Awarded Mar 30, 2019 at 13:00

Ivan Bogush

1096 bronze badges

What is graph clustering?

Awarded Mar 21, 2019 at 22:30

nbro

39.6k12 gold badges101 silver badges181 bronze badges

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?

Awarded Mar 5, 2019 at 14:40

hridayns

2332 silver badges13 bronze badges

Algorithms can be greedy. What are some other algorithmic vices?

Awarded Jan 25, 2019 at 1:15

DukeZhou

6,2375 gold badges25 silver badges53 bronze badges

What kinds of problems can AI solve without using a deep neural network?

Awarded Sep 28, 2018 at 23:10

John Doucette

9,2071 gold badge17 silver badges52 bronze badges

What's the state of the art w.r.t research on the legal aspects of Artificial Intelligence?

Awarded Jun 22, 2018 at 14:24

mindcrime♦

3,75714 silver badges29 bronze badges

How do neural networks manage to do regression?

Awarded Mar 6, 2018 at 7:06

PeterW

2411 silver badge4 bronze badges

Has the Lovelace Test 2.0 been successfully used in an academic setting?

Awarded Jun 11, 2017 at 13:02

Left SE On 10_6_19

1,6609 silver badges23 bronze badges

How to test if my implementation of back propagation neural Network is correct

Awarded Jan 28, 2017 at 15:01

Anas EL KORCHI

1971 silver badge9 bronze badges

Are there any microchips specifically designed to run ANNs?

Awarded Aug 4, 2016 at 6:13

kenorb

10.4k3 gold badges44 silver badges93 bronze badges