DL_Riddle_Quiz 1

Adivinanza

Jugadas 1

Crear copia

Sobre esta actividad

DL_RIDDLE_QUIZ_1

Creada por

Sivaranjini S

India

Descarga la versión para jugar en papel

Top 10 resultados

Todavía no hay resultados para este juego. ¡Sé el primero en aparecer en el ranking! Inicia sesión para identificarte.

Crea tu propio juego gratis desde nuestro creador de juegos

Compite contra tus amigos para ver quien consigue la mejor puntuación en esta actividad

Crear reto

¡Adivina el brawler 1!

😎🎧 Mia Gamer ⭐💥

Perú

(58)

Adivínalo 😁⭐
Adivina el jugador NBA

guillermo .

España

(18)

¿lo conseguirás?
Criaturas fantásticas

Educaplay Educational Resources

España

(31)

Adivínalas usando el menor número de pistas posible
Adivina la seleccion de futbol

Andres Castro

Colombia

(72)

Debes adivinar la selección
adivinador de adivinanzas

juan hoyos

Colombia

(22)

consiste en adivinar palabras de una frase incompleta o sin respuestas


DL_Riddle_Quiz 1Versión en línea DL_RIDDLE_QUIZ_1 por Sivaranjini S 1 I am the family of neural networks that operates over hierarchical input defined by a parse tree. Hints 1 At every parent node I combine my children using a shared weight matrix. 2 I am the alternative name for a transposed convolution emphasising its mathematical role as the gradient-flow operation of a forward strided convolution. Hints 1 I am a misleading term — I am NOT the inverse of convolution and I do NOT recover the original input. 2 People often use my name even though it is technically incorrect. 3 I am the segmentation loss most directly derived from the F1 score. Hints 1 I treat predicted and ground-truth foreground masks symmetrically as sets and penalise their lack of overlap. 2 I struggle when both masks are empty; people add a small ε to my denominator to avoid division by zero. 4 I am U-Net's mechanism for fusing high-resolution encoder features with upsampled decoder features. Hints 1 I do NOT use addition; I append along the channel dimension. 2 DenseNet is the architecture most associated with applying me densely between every pair of layers in a block. 5 I am a small fully-convolutional network that slides a 3×3 window over a shared backbone feature map. Hints 1 I classify each anchor as object/background and regress its bounding-box offset. 2 I replaced selective search and helped make object detection nearly real-time.

DL_Riddle_Quiz 1Versión en línea

DL_RIDDLE_QUIZ_1

por Sivaranjini S

I am the family of neural networks that operates over hierarchical input defined by a parse tree.

Hints

At every parent node I combine my children using a shared weight matrix.

I am the alternative name for a transposed convolution emphasising its mathematical role as the gradient-flow operation of a forward strided convolution.

Hints

I am a misleading term — I am NOT the inverse of convolution and I do NOT recover the original input.

People often use my name even though it is technically incorrect.

I am the segmentation loss most directly derived from the F1 score.

Hints

I treat predicted and ground-truth foreground masks symmetrically as sets and penalise their lack of overlap.

I struggle when both masks are empty; people add a small ε to my denominator to avoid division by zero.

I am U-Net's mechanism for fusing high-resolution encoder features with upsampled decoder features.

Hints

I do NOT use addition; I append along the channel dimension.

DenseNet is the architecture most associated with applying me densely between every pair of layers in a block.

I am a small fully-convolutional network that slides a 3×3 window over a shared backbone feature map.

Hints

I classify each anchor as object/background and regress its bounding-box offset.

I replaced selective search and helped make object detection nearly real-time.

Puedes integrar el juego en un LMS compatible con LTI 1.1 o LTI 1.3 como Canvas, Moodle, o Blackboard. De esta manera podrás guardar las puntuaciones automáticamente en el libro de calificaciones de esa plataforma.

DL_Riddle_Quiz 1

Adivinanza

Sobre esta actividad

Creada por

Descarga la versión para jugar en papel

Top juegos

Adivinanza

¡Adivina el brawler 1!

Adivinanza

Adivina el jugador NBA

Adivinanza

Criaturas fantásticas

Adivinanza

Adivina la seleccion de futbol

Adivinanza

adivinador de adivinanzas

DL_Riddle_Quiz 1Versión en línea

por Sivaranjini S

I am the family of neural networks that operates over hierarchical input defined by a parse tree.

Hints

I am the alternative name for a transposed convolution emphasising its mathematical role as the gradient-flow operation of a forward strided convolution.

Hints

I am the segmentation loss most directly derived from the F1 score.

Hints

I am U-Net's mechanism for fusing high-resolution encoder features with upsampled decoder features.

Hints

I am a small fully-convolutional network that slides a 3×3 window over a shared backbone feature map.

Hints

		%
	Anónimo	%
		%
		%