Chemical implementation of neural networks and Turing machines.
نویسندگان
چکیده
منابع مشابه
Neural Turing Machines
We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-toend, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simp...
متن کاملEvolving Neural Turing Machines
Instead of training a Neural Turing Machine (NTM) with gradient descent [1], in this work NTMs are trained through an evolutionary algorithm. Preliminary results suggest that this setup can greatly simplify the neural model, generalizes better, and does not require accessing the entire memory content at each time-step. We show preliminary results on a simple copy and T-Maze learning task.
متن کاملTowards Chemical Universal Turing Machines
Present developments in the natural sciences are providing enormous and challenging opportunities for various AI technologies to have an unprecedented impact in the broader scientific world. If taken up, such applications would not only stretch present AI technology to the limit, but if successful could also have a radical impact on the way natural science is conducted. We review our experience...
متن کاملReinforcement Learning Neural Turing Machines
The Neural Turing Machine (NTM) is more expressive than all previously considered models because of its external memory. It can be viewed as a broader effort to use abstract external Interfaces and to learn a parametric model that interacts with them. The capabilities of a model can be extended by providing it with proper Interfaces that interact with the world. These external Interfaces includ...
متن کاملLie-Access Neural Turing Machines
External neural memory structures have recently become a popular tool for algorithmic deep learning (Graves et al., 2014; Weston et al., 2014). These models generally utilize differentiable versions of traditional discrete memory-access structures (random access, stacks, tapes) to provide the storage necessary for computational tasks. In this work, we argue that these neural memory systems lack...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the National Academy of Sciences
سال: 1991
ISSN: 0027-8424,1091-6490
DOI: 10.1073/pnas.88.24.10983