GKozinski's user avatar
GKozinski's user avatar
GKozinski's user avatar
GKozinski
  • Member for 5 years
  • Last seen more than a month ago
  • Warsaw, Polska
9 votes
3 answers
6k views

Is a GPU always faster than a CPU for training neural networks?

7 votes
1 answer
407 views

What is the best measure for detecting overfitting?

5 votes
1 answer
456 views

Why evolutionary training of neural networks is not popular?

4 votes
1 answer
115 views

Is there any measure of separability of classes?

4 votes
1 answer
746 views

What does 'democratizing AI' exactly mean?

4 votes
2 answers
644 views

What algorithms are used in Artificial General Intelligence research?

3 votes
1 answer
72 views

Are there deep neural networks that have inputs connected with deeper hidden layers?

3 votes
0 answers
187 views

Can XGBoost solve XOR problem?

3 votes
1 answer
60 views

Can a model, retrained on images classified previously by itself, increase its accuracy?

3 votes
1 answer
103 views

How to draw bounding boxes for gender classification?

3 votes
1 answer
422 views

Can dropout layers not influence LSTM training?

3 votes
1 answer
690 views

What are evolutionary algorithms for topology and weights evolving of ANN (TWEANN) other than NEAT?

2 votes
1 answer
191 views

What are modern state-of-the-art solutions in prediction of time-series?

2 votes
3 answers
398 views

How to deal with random weights initialization in hyperparameters tuning?

2 votes
1 answer
60 views

Why tf object detection api needs so few pictures?

2 votes
0 answers
29 views

Can two neural networks be better instead of one with a categorical feature?

2 votes
1 answer
712 views

Can an RL algorithm trained in one environment be successful in a different one?

2 votes
1 answer
91 views

Is there a clustering algorithm that can make n clusters and the n+1 "others" cluster?

2 votes
2 answers
86 views

How general is generalization?

1 vote
1 answer
137 views

Should I use single or double view for gender recognition?

1 vote
1 answer
110 views

How to ensure continuity of AI model logic?

1 vote
1 answer
550 views

How to deal with evolutionary/genetic fitness function that can have both negative and positive values?

1 vote
0 answers
59 views

Are there regularisation methods related only to architecture of the CNNs?

1 vote
1 answer
82 views

Should binary feature be in one or two columns in deep neural networks?

1 vote
0 answers
61 views

Is there a difference between using 1d conv layers and 2d conv layers with kernel with size of 1 along other than time dimension?

1 vote
1 answer
126 views

Can the optimal learning rate differ for different architectures?

1 vote
2 answers
30 views

How to properly name given type of classification problem?

1 vote
1 answer
68 views

What loss function will be correlated with classification metrics?

1 vote
1 answer
66 views

Why training the same model on the same data can be slower on better card?

1 vote
1 answer
610 views

How do I identify the number and type of objects in the same picture?