arXiv subjects

Natesh Ganesh

Publications and source records attributed to Natesh Ganesh.

6 recordsLinked to original sources

arXiv2023

Multiplexed gradient descent: Fast online training of modern datasets on hardware neural networks without backpropagation

We present multiplexed gradient descent (MGD), a gradient descent framework designed to easily train analog or digital neural networks in hardware. MGD utilizes zero-order optimization techniques for online training of hardware neural networks. We demonstrate its ability to train neural networks on modern machine learning datasets, including CIFAR-10 and Fashion-MNIST, and compare its performance to backpropagation. Assuming realistic timescales and hardware parameters, our results indicate that these optimization techniques can train a network on emerging hardware platforms orders of magnitude faster than the wall-clock time of training via backpropagation on a standard GPU, even in the presence of imperfect weight updates or device-to-device variations in the hardware. We additionally describe how it can be applied to existing hardware as part of chip-in-the-loop training, or integrated directly at the hardware level. Crucially, the MGD framework is highly flexible, and its gradient descent process can be optimized to compensate for specific hardware limitations such as slow parameter-update speeds or limited input bandwidth.

cs.LG↗

arXiv2021

No Substitute for Functionalism -- A Reply to 'Falsification & Consciousness'

In their paper 'Falsification and Consciousness' [1], Kleiner and Hoel introduced a formal mathematical model of the process of generating observable data from experiments and using that data to generate inferences and predictions onto an experience space. The resulting substitution argument built on this framework was used to show that any theory of consciousness with independent inference and prediction data are pre-falsified, if the inference reports are considered valid. If this argument does indeed pre-falsify many of the leading theories of consciousness, it would indicate a fundamental problem affecting the field of consciousness as a whole that would require radical changes to how consciousness science is performed. In this reply, the author will identify avenues of expansion for the model proposed in [1], allowing us to distinguish between different types of variation. Motivated by examples from neural networks, state machines and Turing machines, we will prove that substitutions do not exist for a very broad class of Level-1 functionalist theories, rendering them immune to the aforementioned substitution argument.

cs.OH↗

arXiv2021

From Quantifying Vagueness To Pan-niftyism

In this short paper, we will introduce a simple model for quantifying philosophical vagueness. There is growing interest in this endeavor to quantify vague concepts of consciousness, agency, etc. We will then discuss some of the implications of this model including the conditions under which the quantification of `nifty' leads to pan-nifty-ism. Understanding this leads to an interesting insight - the reason a framework to quantify consciousness like Integrated Information Theory implies (forms of) panpsychism is because there is favorable structure already implicitly encoded in the construction of the quantification metric.

cs.AI↗

arXiv2020

Rebooting Neuromorphic Hardware Design -- A Complexity Engineering Approach

As the compute demands for machine learning and artificial intelligence applications continue to grow, neuromorphic hardware has been touted as a potential solution. New emerging devices like memristors, atomic switches, etc have shown tremendous potential to replace CMOS-based circuits but have been hindered by multiple challenges with respect to device variability, stochastic behavior and scalability. In this paper we will introduce a Description<->Design framework to analyze past successes in computing, understand current problems and identify solutions moving forward. Engineering systems with these emerging devices might require the modification of both the type of descriptions of learning that we will design for, and the design methodologies we employ in order to realize these new descriptions. We will explore ideas from complexity engineering and analyze the advantages and challenges they offer over traditional approaches to neuromorphic design with novel computing fabrics. A reservoir computing example is used to understand the specific changes that would accompany in moving towards a complexity engineering approach. The time is ideal for a significant reboot of our design methodologies and success will represent a radical shift in how neuromorphic hardware is designed and pave the way for a new paradigm.

cs.ET↗

arXiv2020

A Non-equilibrium Thermodynamic Framework of Consciousness

In this paper, we take a brief look at the advantages and disadvantages of dominant frameworks in consciousness studies -- functionalist and causal structure theories, and use it to motivate a new non-equilibrium thermodynamic framework of consciousness. The main hypothesis in this paper will be two thermodynamic conditions obtained from the non-equilibrium fluctuation theorems -- TCC 1 and 2, that the author proposes as necessary conditions that a system will have to satisfy in order to be 'conscious'. These descriptions will look to specify the functions achieved by a conscious system and restrict the physical structures that achieve them without presupposing either of the two. These represent an attempt to integrate consciousness into established physical law (without invoking untested novel frameworks in quantum mechanics and/or general relativity). We will also discuss it's implications on a wide range of existing questions, including a stance on the hard problem. The paper will also explore why this framework might offer a serious path forward to understanding consciousness (and perhaps even realizing it in artificial systems) as well as laying out some problems and challenges that lie ahead.

cs.AI↗

arXiv2019

Thermodynamic Computing

The hardware and software foundations laid in the first half of the 20th Century enabled the computing technologies that have transformed the world, but these foundations are now under siege. The current computing paradigm, which is the foundation of much of the current standards of living that we now enjoy, faces fundamental limitations that are evident from several perspectives. In terms of hardware, devices have become so small that we are struggling to eliminate the effects of thermodynamic fluctuations, which are unavoidable at the nanometer scale. In terms of software, our ability to imagine and program effective computational abstractions and implementations are clearly challenged in complex domains. In terms of systems, currently five percent of the power generated in the US is used to run computing systems - this astonishing figure is neither ecologically sustainable nor economically scalable. Economically, the cost of building next-generation semiconductor fabrication plants has soared past $10 billion. All of these difficulties - device scaling, software complexity, adaptability, energy consumption, and fabrication economics - indicate that the current computing paradigm has matured and that continued improvements along this path will be limited. If technological progress is to continue and corresponding social and economic benefits are to continue to accrue, computing must become much more capable, energy efficient, and affordable. We propose that progress in computing can continue under a united, physically grounded, computational paradigm centered on thermodynamics. Herein we propose a research agenda to extend these thermodynamic foundations into complex, non-equilibrium, self-organizing systems and apply them holistically to future computing systems that will harness nature's innate computational capacity. We call this type of computing "Thermodynamic Computing" or TC.

cs.CY↗