本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
16. そして宣言通り完走
16
SUN MON TUE WED THU FRI SAT
1
Robotic Pick-and-
Place of Novel
Objects in Clutter
with …
2
FCN-Based 6D
Robotic Grasping
for Arbitrary
Placed Objects
3
Deep vision
networks for real-
time robotic grasp
detection
4
Learning Hand-Eye
Coordination for
Robotic Grasping
with Deep …
5
Supersizing Self-
supervision:
Learning to Grasp
from 50K Tries …
6
End-to-End
Training of Deep
Visuomotor Policies
7
Real-Time Object
Detection,
Localization and
Verification …
8
Grasping Novel
Objects with Depth
Segmentation
9
Robot grasp
detection using
multimodal deep
convolutional …
10
SSH: Single Stage
Headless Face
Detector
11
R-FCN: Object
Detection via
Region-based
Fully …
12
R-FCN-3000 at
30fps: Decoupling
Detection and
Classification…
13
Progressive
Growing of GANs
for Improved
Quality, Stability, …
14
Learning a Rotation
Invariant Detector
with Rotatable
Bounding Box
15
Interactively
Picking Real-World
Objects with
Unconstrained …
16
Deep Object-
Centric
Representations for
Generalizable …
17
Single-Shot
Refinement Neural
Network for Object
Detection
18
Sushi Dish : Object
detection and
classification from
real images
19
MarrNet: 3D Shape
Reconstruction via
2.5D Sketches
20
2D-Driven 3D
Object Detection in
RGB-D Images
21
Action Tubelet
Detector for Spatio-
Temporal Action
Localization
22
Generative
Adversarial
Networks
Conditioned by …
23
SSD-6D: Making
RGB-Based 3D
Detection and 6D
Pose Estimation …
24
Unsupervised
Creation of
Parameterized
Avatars
25
Scene Graph
Generation from
Objects, Phrases
and Region …
26
UberNet : Training
a ‘Universal’
Convolutional
Neural Network …
27
Learning non-
maximum
suppression
28
Annotating Object
Instances with a
Polygon-RNN
29
Multi-View 3D
Object Detection
Network for
Autonomous …
30
GuessWhat?!
Visual object
discovery through
multi-modal …
31
Cognitive Mapping
and Planning for
Visual Navigation