Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 5
Merjenje atmosferskih parametrov
Jure Vreča, Iztok Kramberger
Diplomsko delo
Oznake: temperatura;tlak;relativna vlažnost;koncentracija trdnih delcev;vremenski balon;projektne naloge;
V projektni nalogi smo predstavili zasnovo elektronskega sistema za samodejno merjenje naslednjih parametrov atmosfere: temperatura, pritisk, relativna vlažnost in koncentracija trdnih delcev. Elektronski sistem smo zasnovali s ciljem izvajanja samodejnih meritev na vremenskem balonu. Uporabili smo ...
Leto: 2017 Vir: Fakulteta za elektrotehniko, računalništvo in informatiko (UM FERI)
ǂA ǂconfigurable mixed-precision convolution processing unit generator in Chisel
Jure Vreča, Anton Biasizzo
Objavljeni znanstveni prispevek na konferenci
Oznake: nevronske mreže;Chisel;FPGA;neural networks;quantization;
Leto: 2023 Vir: Institut Jožef Stefan (IJS)
Towards deploying highly quantized neural networks on FPGA using chisel
Jure Vreča, Anton Biasizzo
Objavljeni znanstveni prispevek na konferenci
Oznake: neural networks;QKeras;Chisel4ml;
We present chisel4ml, a Chisel-based tool that generates hardware for highly quantized neural networks described in QKeras. Such networks typically use parameters with bitwidths less than 8 bits and may have pruned connections. Chisel4ml can generate the highly quantized neural network as a single c ...
Leto: 2023 Vir: Institut Jožef Stefan (IJS)
Deep learning on low power embedded devices using RISC-V cores with an extended instruction set
Jure Vreča, Zmago Brezočnik, Farhad Merchant
Magistrsko delo
Oznake: deep learning;embedded system;instruction set;RISC-V;
This thesis explores the possibility of running neural networks on microcontrollers and how to optimize their performance using instruction set extensions. Microcontrollers are seen as too weak to run neural networks. We challenge this view and show that stripped-down neural networks can run and ...
Leto: 2020 Vir: Fakulteta za elektrotehniko, računalništvo in informatiko (UM FERI)
Hardware–software co-design of an audio feature extraction pipeline for machine learning applications
Jure Vreča, Ratko Pilipović, Anton Biasizzo
Izvirni znanstveni članek
Oznake: FPGA;MFCC;keyword spotting;chisel;
Keyword spotting is an important part of modern speech recognition pipelines. Typical contemporary keyword-spotting systems are based on Mel-Frequency Cepstral Coefficient (MFCC) audio features, which are relatively complex to compute. Considering the always-on nature of many keyword-spotting system ...
Leto: 2024 Vir: Institut Jožef Stefan (IJS)
Št. zadetkov: 5
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: