Search: deepmind.com | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

FermiNet: Quantum Physics and Chemistry from First Principles

6 years ago

122 points

62.

Discovering Novel Algorithms with AlphaTensor

4 years ago

117 points

63.

Tackling multiple tasks with a single visual language model

4 years ago

114 points

64.

Reinforcement learning with unsupervised auxiliary tasks

10 years ago

102 points

65.

AlphaGo Teach – Find new and creative ways of playing Go

alphagoteach.deepmind.com

9 years ago

99 points

66.

MuZero’s first step from research into the real world

4 years ago

91 points

67.

Specification gaming: the flip side of AI ingenuity

6 years ago

91 points

68.

Exploring the beauty of pure mathematics in novel ways

5 years ago

88 points

69.

Agent57: Outperforming the human Atari benchmark

6 years ago

87 points

70.

Advancing Sports Analytics Through AI Research

5 years ago

78 points

71.

Capture the Flag: the emergence of complex cooperative agents

7 years ago

73 points

72.

AlphaStar: Grandmaster Level in StarCraft II

7 years ago

68 points

73.

Improving Language Models by Retrieving from Trillions of Tokens

5 years ago

64 points

74.

Deepmind – Reinforcement Learning Lecture Series (2021)

3 years ago

60 points

75.

Using JAX to Accelerate Research

6 years ago

54 points

76.

Replay in biological and artificial neural networks

7 years ago

51 points

77.

Safety-first AI for autonomous data centre cooling and industrial control

8 years ago

50 points

78.

AndroidEnv: The Android Learning Environment

5 years ago

46 points

79.

Open sourcing TRFL: a library of reinforcement learning building blocks

8 years ago

44 points

80.

Grandmaster level in StarCraft II using multi-agent reinforcement learning

7 years ago

42 points

81.

Red-teaming language models with language models

4 years ago

40 points

82.

Learning human objectives by evaluating hypothetical behaviours

7 years ago

39 points

83.

Realizing scientists are the real superheroes

4 years ago

37 points

84.

DeepMind Achieves Human Level Performance in Quake III Arena Capture the Flag

7 years ago

34 points

85.

Predicting Patient Deterioration

7 years ago

31 points

86.

Fast reinforcement learning through composition of behavior

6 years ago

29 points

87.

Capture the Flag: the emergence of complex cooperative agents

8 years ago

29 points

88.

Differentiable neural computers

10 years ago

24 points

89.

Nowcasting the Next Hour of Rain

5 years ago

RageoftheRobots

24 points

90.

DeepMind Papers at NIPS (Part 1)

10 years ago

21 points