In this paper, we present a novel artificial intelligence (AI) program that identifies pulsars from recent surveys using image pattern recognition with deep neural nets---the PICS (Pulsar Image-based Classification System) AI. The AI mimics human exp
erts and distinguishes pulsars from noise and interferences by looking for patterns from candidate. The information from each pulsar candidate is synthesized in four diagnostic plots, which consist of up to thousands pixel of image data. The AI takes these data from each candidate as its input and uses thousands of such candidates to train its ~9000 neurons. Different from other pulsar selection programs which use pre-designed patterns, the PICS AI teaches itself the salient features of different pulsars from a set of human-labeled candidates through machine learning. The deep neural networks in this AI system grant it superior ability in recognizing various types of pulsars as well as their harmonic signals. The trained AIs performance has been validated with a large set of candidates different from the training set. In this completely independent test, PICS ranked 264 out of 277 pulsar-related candidates, including all 56 previously known pulsars, to the top 961 (1%) of 90008 test candidates, missing only 13 harmonics. The first non-pulsar candidate appears at rank 187, following 45 pulsars and 141 harmonics. In other words, 100% of the pulsars were ranked in the top 1% of all candidates, while 80% were ranked higher than any noise or interference. The performance of this system can be improved over time as more training data are accumulated. This AI system has been integrated into the PALFA survey pipeline and has discovered six new pulsars to date.
PSR J1740-3052 is a young pulsar in orbit around a companion that is most likely a B-type main-sequence star. Since its discovery more than a decade ago, data have been taken at several frequencies with instruments at the Green Bank, Parkes, Lovell,
and Westerbork telescopes. We measure scattering timescales in the pulse profiles and dispersion measure changes as a function of binary orbital phase and present evidence that both of these vary as would be expected due to a wind from the companion star. Using pulse arrival times that have been corrected for the observed periodic dispersion measure changes, we find a timing solution spanning 1997 November to 2011 March. This includes measurements of the advance of periastron and the change in the projected semimajor axis of the orbit and sets constraints on the orbital geometry. From these constraints, we estimate that the pulsar received a kick of at least ~50 km/s at birth. A quasi-periodic signal is present in the timing residuals with a period of 2.2 times the binary orbital period. The origin of this signal is unclear.
