Femtosecond pulse compression using a neural-network algorithm.

A key requirement for femtosecond spectroscopy measurements is to compress the laser pulse to its transform-limited duration. In particular, for few-cycle laser pulses, the compression process is time-consuming using conventional algorithms that converge statistically. Here we show that machine learning can accelerate the process of pulse compression: we have developed an adaptive neural-network algorithm to control a deformable-mirror-based pulse shaper that converges 100× faster than a standard evolutionary algorithm.

[1]  P. Becker,et al.  Compression of optical pulses to six femtoseconds by using cubic phase compensation. , 1987, Optics letters.

[2]  Tong Heng Lee,et al.  Real-time parallel adaptive neural network control for nonlinear servomechanisms—an approach using direct adaptive techniques , 1993 .

[3]  J G Fujimoto,et al.  Generation of 5-fs pulses and octave-spanning spectra directly from a Ti:sapphire laser. , 2001, Optics letters.

[4]  W. Kinzel,et al.  Modeling of light-matter interactions with neural networks , 2007 .

[5]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[6]  Derryck T. Reid,et al.  Programmable spectral phase control of femtosecond pulses by use of adaptive optics and real-time pulse measurement , 2004 .

[7]  T. Baumert,et al.  Femtosecond pulse shaping by an evolutionary algorithm with feedback , 1997 .

[8]  J. Gagnon,et al.  Synthesized Light Transients , 2011, Science.

[9]  X Zhu,et al.  Remote characterization and dispersion compensation of amplified shaped femtosecond pulses using MIIPS. , 2006, Optics express.

[10]  Fiorenzo G. Omenetto,et al.  Genetic algorithm pulse shaping for optimum femtosecond propagation in optical fibers , 1999 .

[11]  Huiyong Wang,et al.  A Bayesian regularized artificial neural network for adaptive optics forecasting , 2017 .

[12]  Peter Schunemann,et al.  High-energy mid-infrared sub-cycle pulse synthesis from a parametric amplifier , 2016, Nature Communications.

[13]  Reimer Selle,et al.  Modelling of ultrafast coherent strong-field dynamics in potassium with neural networks , 2008 .

[14]  Gleb Vdovin.  Model of an adaptive optical system controlled by a neural network , 1995 .

[15]  Daniel B. Turner,et al.  Resolving molecular vibronic structure using high-sensitivity two-dimensional electronic spectroscopy. , 2015, The Journal of chemical physics.

[16]  A. Weiner.  Femtosecond pulse shaping using spatial light modulators , 2000 .

[17]  V. Prokhorenko,et al.  Coherent control of the population transfer in complex solvated molecules at weak excitation. An experimental study. , 2005, The Journal of chemical physics.

[18]  Albert Y. Zomaya.  Reinforcement learning for the adaptive control of nonlinear systems , 1994 .

[19]  J. Gordon,et al.  Negative dispersion using pairs of prisms. , 1984, Optics letters.

[20]  B. Eggleton,et al.  High-energy pulse synthesis with sub-cycle waveform control for strong-field physics , 2011 .

[21]  Joshua C Vaughan,et al.  Multidimensional control of femtosecond pulses by use of a programmable liquid-crystal matrix. , 2002, Optics letters.

[22]  Noah Flemens,et al.  Generation and multi-octave shaping of mid-infrared intense single-cycle pulses , 2017, Nature Photonics.

[23]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[24]  V Pervak,et al.  Invited article: attosecond photonics: synthesis and control of light transients. , 2012, The Review of scientific instruments.

[25]  Ulrich A. Russek,et al.  Pulse compression by use of deformable mirrors. , 1999, Optics letters.

[26]  E. Goulielmakis,et al.  Optical attosecond pulses and tracking the nonlinear response of bound electrons , 2016, Nature.

[27]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[28]  Francisco Javier de Cos Juez,et al.  Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems , 2017, Sensors.