Francisco Algaba de la Vieja

Francisco Algaba de la Vieja

Greater Madrid Metropolitan Area
2K followers 500+ connections

Join to view profile

Activity

Join now to see all activity

Experience

  • Giza Graphic

    Giza

  • -

    Madrid, Comunidad de Madrid, España

  • -

    Madrid, Comunidad de Madrid, España

  • -

    Madrid y alrededores

  • -

    Madrid y alrededores

  • -

    Madrid, Comunidad de Madrid, España

  • -

    Madrid y alrededores

  • -

    Madrid y alrededores, España

  • -

    Madrid y alrededores, España

  • -

    Madrid y alrededores, España

  • -

    Madrid y alrededores, España

Education

  • Stanford University Graphic

    Stanford University

    -

    -

    The Deep Learning Specialization is designed to prepare learners
    to participate in the development of cutting-edge AI technology,
    and to understand the capability, the challenges, and the
    consequences of the rise of deep learning. Through five
    interconnected courses, learners develop a profound knowledge
    of the hottest AI algorithms, mastering deep learning from its
    foundations (neural networks) to its industry applications
    (Computer Vision, Natural Language Processing…

    The Deep Learning Specialization is designed to prepare learners
    to participate in the development of cutting-edge AI technology,
    and to understand the capability, the challenges, and the
    consequences of the rise of deep learning. Through five
    interconnected courses, learners develop a profound knowledge
    of the hottest AI algorithms, mastering deep learning from its
    foundations (neural networks) to its industry applications
    (Computer Vision, Natural Language Processing, Speech
    Recognition, etc.).

  • -

  • -

    -

Licenses & Certifications

Join now to see all certifications

Publications

  • Coordination between robotic arm and camera using Deep Reinforcement Learning

    Development of a humanoid robotic arm with a laser pointer at its end capable of aiming where a camera is looking using a deep reinforcement learning technique called Deep Q-learning (DQN). We present an approach that uses three dimensional (3D) simulations to train this three-joint robotic arm in this task without any prior knowledge of the environment or the arm kinematics. The agent uses as input the distance between the point the arm is aiming and the point where the camera in this case is…

    Development of a humanoid robotic arm with a laser pointer at its end capable of aiming where a camera is looking using a deep reinforcement learning technique called Deep Q-learning (DQN). We present an approach that uses three dimensional (3D) simulations to train this three-joint robotic arm in this task without any prior knowledge of the environment or the arm kinematics. The agent uses as input the distance between the point the arm is aiming and the point where the camera in this case is looking and outputs motor actions. The space of states has a very high dimensionality, so the use of discretization and a proper reward system is needed for learning the policy. Our results demonstrate that the use of DQN can be used to learn control policies that solve our proposed task. The agent demonstrates great performance when it needs to generalize when its faced to unfamiliar environments. Even so, the ability to generalize using deep reinforcement learning needs further research.

    See publication

Languages

  • Español

    Native or bilingual proficiency

  • Ingles

    Full professional proficiency

More activity by Francisco

View Francisco’s full profile

  • See who you know in common
  • Get introduced
  • Contact Francisco directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Add new skills with these courses

See all courses